Designing Cloud Landing Zones by Traffic Flow: A Defence‑in‑Depth, DMZ‑First Architecture
As enterprises adopt Microsoft Azure for large‑scale and regulated workloads, security architecture must be driven by traffic trust boundaries and inspection intent, not connectivity alone. Regulatory frameworks consistently require a clear separation between Internet‑untrusted and private enterprise traffic, enforced through defence‑in‑depth controls aligned to the OSI model. This drives the adoption of a DMZ‑first landing zone architecture, where volumetric protection, application‑layer inspection, and perimeter controls are enforced at well‑defined trust boundaries. Security enforcement is prioritised before access, rather than being an afterthought of connectivity. A distributed hub architecture enables this model at scale, delivering consistent controls while improving resiliency, fault isolation, and operational clarity. Traffic Classification in an Enterprise Landing Zone Enterprise traffic flows are classified based on origin, destination, and trust level, which directly dictates inspection requirements: Internet Inbound (North–South): Traffic from the public Internet to Azure‑hosted applications Internet Outbound (South–North): Egress traffic from private workloads to the Internet East–West: Traffic between virtual networks within or across regions Hybrid Connectivity: Traffic between Azure, on‑premises, and multi‑cloud environments Each flow presents a distinct risk profile, making a uniform connectivity and inspection model unsuitable for enterprise and regulated environments. Hub‑and‑Spoke as the Foundation for Centralised Security Enterprises commonly adopt a Hub‑and‑Spoke topology using VNET peering or Azure Virtual WAN, extending hybrid connectivity via Site‑to‑Site VPN or ExpressRoute. The hub provides a centralised, datapath‑centric layer for shared networking and security services, while spoke VNETs host application workloads and remain private, typically without public IPs. Ingress and egress are handled through shared, centrally managed endpoints. This model consolidates critical controls—Azure Firewall, Azure WAF, and DDoS protection—at controlled entry and exit points, significantly reducing the attack surface. Integration with Microsoft Sentinel enables cross‑layer visibility, threat hunting, and detection of risks such as unauthorised access and data exfiltration. Why a Single Hub Is Not Sufficient Using a single hub to process all traffic types introduces operational and security challenges at scale by forcing Internet‑untrusted and private traffic through the same inspection tier. Key limitations include: Coupled Internet and private security policies Rapid firewall rule sprawl and management overhead A single blast radius across all traffic types Throughput and SNAT scalability constraints Increased difficulty meeting regulatory separation requirements These issues become more pronounced as environments scale across regions and workloads. Multi‑Hub as an Enterprise‑Grade Evolution A multi‑hub architecture resolves these challenges by separating inspection responsibilities across dedicated hubs: DMZ Hub VNET: Internet‑facing traffic and perimeter security enforcement Core Hub VNET: Outbound Internet access, East‑West, and hybrid traffic inspection This separation aligns security controls with traffic intent, reduces policy complexity, limits blast radius, and simplifies operations. In the next section, we explore multi‑hub architecture patterns and examine how each traffic flow is inspected and governed in practice. Scenario 1 – Third‑Party Firewall–Centric Multi‑Hub Design In this scenario, third‑party firewalls provide inspection for all traffic flows—Internet inbound, Internet outbound, East‑West, and hybrid connectivity—while Azure WAF and Azure DDoS Protection are used to defend against volumetric attacks, application‑layer threats, and malicious bot traffic. Architecture Overview The design uses two dedicated hub virtual networks, with spoke VNets peered to both hubs to maintain traffic separation based on trust and inspection requirements: DMZ Hub VNET (Internet Ingress Hub) Core Hub VNET (Egress, East‑West, and Hybrid Hub) DMZ Hub VNET – Internet Inbound (North–South) Traffic The DMZ hub establishes a dedicated perimeter for Internet‑facing applications. Internet traffic lands on a public Application Gateway with Azure WAF, protected by an Azure DDoS Protection Plan applied to the public frontend IP. Third‑party firewalls are deployed behind the Application Gateway to perform deep packet inspection. Firewalls operate in active‑active mode as standalone appliances, using three dedicated network interfaces (Untrust, Trust, and Management), each placed in separate subnets. Application Gateway provides load balancing and health probing, ensuring firewall availability and resiliency. Core Hub VNET – Egress, East‑West, and Hybrid Traffic The core hub handles all non‑Internet‑inbound traffic flows, including private inter‑VNET communication and hybrid connectivity. Third‑party firewalls are deployed behind an internal Azure Load Balancer, which maintains high availability using health probes. Firewalls follow the same active‑active, three‑NIC design for consistent policy enforcement and operational symmetry. Azure NAT Gateway is associated with the firewall Untrust subnet to scale outbound SNAT and simplify Internet egress with deterministic public IP. Site‑to‑site VPN or ExpressRoute terminate in this hub for on‑premises and multi‑cloud connectivity, ensuring private and regulated traffic bypasses Internet‑facing controls. Architecture Patterns - Traffic Flow 1.1 North–South (Internet Inbound) Traffic Flow This flow applies when applications hosted on Azure (VMs, VM Scale Sets, or services behind Internal Load Balancer / Internal Application Gateway) are published to the Internet. As shown in the diagram, Internet-bound client requests enter Azure through a dedicated DMZ Hub, where perimeter security controls are enforced before traffic reaches private application spokes. Inbound Request Flow (Blue Path) Client → Application Gateway (WAF) A client request (for example, app1.example.com) is resolved via DNS and lands on the public endpoint of Azure Application Gateway. Azure WAF performs Layer‑7 inspection, bot protection, and rule evaluation. Application Gateway → Firewall (DMZ Hub) Based on hostname and routing rules, Application Gateway forwards traffic to the firewalls while preserving the client’s real IP using the X‑Forwarded‑For (XFF) header. Firewall → Application (Spoke VNET) The firewall performs DNAT to the internal destination (Internal Application Gateway or Internal Load Balancer) and SNAT to its trust‑interface IP to ensure symmetric return traffic. Traffic is then routed over VNET peering to the private application workload. Response Flow (Green Path) Application → Firewall The application responds using its private IP, with the firewall trust interface as the destination. Firewall → Application Gateway The firewall forwards the response based on its session state. Application Gateway → Client Application Gateway returns the response to the Internet client. DDoS Protection Azure DDoS Protection continuously monitors the Application Gateway public IP and mitigates volumetric attacks before they reach the application stack. Key Design Considerations Application Gateway routing - Use a multi‑site listener with hostname‑based rules to steer traffic to the appropriate firewall backend. Firewall backend mapping - Register firewall VMs in a single backend pool and differentiate applications using distinct backend settings (same protocol, different ports). Application steering at firewall - Firewalls perform port‑based DNAT (or private FQDN‑based DNAT where supported) to forward traffic to the correct application private IP in spoke VNets. Traffic symmetry - Source NAT is applied on the firewall trust interface to maintain symmetric return paths. Protocol support - The same pattern applies to TCP/UDP workloads, using an External Azure Load Balancer instead of Application Gateway where WAF is not required. Client IP visibility Application Gateway enables WAF inspection using the real client IP, preserved downstream via X‑Forwarded‑For. With Azure Load Balancer, client IP is retained up to the firewall for IP‑based enforcement, with Azure DDoS Protection safeguarding the public frontend. 1.2 Hybrid Connectivity Traffic Flow Hybrid connectivity represents communication between Azure workloads and on‑premises environments using Site‑to‑Site VPN or ExpressRoute. Traffic Flow Request (Blue: 1–4): Traffic originates from applications in spoke VNETs and is forwarded via UDRs to the Internal Load Balancer, through active‑active firewalls, and then to on‑premises via VPN or ExpressRoute. Response (Green: 5–8): Return traffic follows the same path in reverse. Key Design Considerations Source and destination IP addresses remain unchanged end‑to‑end, despite firewalls operating behind an Internal Load Balancer. UDRs steer both outbound and inbound hybrid traffic to the Internal Load Balancer as the next hop. Azure Virtual Network Manager can be used to manage and scale UDR deployment centrally across Hub and spoke networks. 1.3 East-West Traffic flow This traffic flow represents the connectivity between resources across VNETs through Firewall. Considerations remain same as “Hybrid Connectivity Traffic flow” mentioned above. 1.4 Egress/Outbound Connectivity Traffic flow This traffic flow represents the connectivity from the resources hosted inside VNETs to Internet through Firewalls deployed behind Internal Load Blancer in Core Hub VNET. Key Considerations: A default route (0.0.0.0/0) UDR directs Internet-bound traffic to the Internal Load Balancer for firewall inspection. Firewall performs SNAT to its untrusted interface, after which Azure NAT Gateway translates traffic to a fixed public IP. Alternatively, a public IP can be assigned to the firewall untrusted interface to perform SNAT directly, removing the need for NAT Gateway and reducing cost. However, with horizontal firewall scaling, outbound public IPs become non-deterministic. Scenario 2: Third‑Party Firewalls for Ingress, Azure Firewall for Private Flows In this scenario, third‑party firewalls secure Internet‑facing traffic, while Azure Firewall handles Egress, East–West, and Hybrid flows. This separation enables organisations to retain existing perimeter security investments while adopting a fully managed, cloud‑native control and data plane for internal traffic flows. As private traffic patterns scale, particularly for chatty East–West communication, Azure Firewall helps simplify operations and improves scalability by offloading traffic inspection to a managed service. This approach reduces operational overhead and provides consistent policy enforcement across internal and hybrid flows. Setup DMZ Hub design remains unchanged from Scenario 1. Core Hub VNET use Azure Firewall for better scalability, built‑in resilience, and simplified operations. Azure Firewall eliminates the need for load balancers and reduces complexity for chatty east‑west traffic. It requires a single subnet (unless force tunnelling is enabled), optimising IP consumption. Outbound traffic is SNATed by Azure Firewall and further translated via Azure NAT Gateway. Firewall‑based SNAT to public IP can be used to avoid NAT Gateway costs when deterministic egress IPs or higher SNAT scale are not required. Traffic Flow North–South (Internet Inbound) Traffic Flow represented with Numbers. Request flow represented with Blue: 1–3 Response flow represented with Brown: 4–6 Egress/Outbound Connectivity Traffic flow represented with alphabets. Request flow represented with Green: A–C Response flow represented with Blue: D–F Hybrid flow represented with purple Architecture Diagram: Further if you want to use Azure Firewall for the Internet Ingress flow, you can use it as well. Below is the architecture diagram explaining the same pattern. Key Considerations: Application Gateway behaviour remains the same as Scenario 1; however, backend pools use IP‑based targets. Internal applications should be exposed via internal Application Gateway or internal load balancer to provide stable backend IPs. Firewall Private IP could be configured as Target of Application Gateway but then Firewall is required to Source and Destination NATing as in case of 3 rd party FWs. For non-web (TCP/UDP) workloads, applications can be directly exposed through the firewall public IP, with Azure DDoS Protection applied to mitigate volumetric attacks. Scenario 3 - Overcoming Peering Complexity at Scale with Azure Virtual WAN In environments where each application is hosted in its own dedicated VNET for isolation and stronger security, a traditional hub‑and‑spoke model quickly becomes complex. With a single hub, "N" spoke VNETs require "N" peering's; introducing multiple hubs increases this to "2N", significantly amplifying operational overhead—especially across multiple regions. Azure Virtual WAN addresses this challenge by eliminating the need for extensive VNET peering. As a global, managed service, it simplifies large‑scale and multi‑region architectures while providing built‑in scalability and operational consistency. Setup DMZ Hub design and components remain unchanged from Scenario 1 keeping defense in depth principles intact for Internet Inbound or North-South traffic. Core Hub VNET is replaced with Azure Virtual WAN Secure Hub which has Azure Firewall inside the managed Secure Hub VNETs. This further eliminates the need for creating Azure Firewall Subnet, Azure NAT Gateway resources for East-West, Egress and Hybrid connectivity and provides same level of security protection as mentioned in Scenario 2. Secure Hub design using Virtual WAN removes the routing and inspection complexity which was unless required in Scenario 2 by removing UDR configurations in Spoke VNETs, Gateway Subnet and Azure Firewall Subnet. This provides simplified design and operations with built-in resiliency by leveraging the managed platform. Azure Firewall eliminates the need for load balancers and reduces complexity for chatty east‑west traffic. East-West, Egress, and Hybrid connectivity happens via VPN Gateway and Express Route Gateway present in Virtual Hub. All private and Internet Egress traffic is inspected by Azure Firewall present in secure Hub. Outbound traffic is SNATed to Public IP by Azure Firewall thus avoiding the need of Azure NAT Gateway. Firewall‑based SNAT to public IP can be used to avoid NAT Gateway costs when deterministic egress IPs or higher SNAT scale are not required. Traffic Flow North–South (Internet Inbound) Traffic Flow represented with Numbers. Request flow represented with Blue: 1–5 Response flow represented with Green: 6–10 Egress/Outbound Connectivity Traffic flow represented with Red Hybrid flow represented with Green East-West connectivity flow represented with black Architecture Diagram: Key Considerations Virtual WAN has additional cost Refer to architecture diagram above for different traffic flows. The DMZ VNET components consideration remains same as per scenario 1 You can use your own managed public IP on Azure Firewall for applying standard IP/Network DDoS protection plan. Benefits of multi-Hub approach over single Hub You can use this table as decision matrix to choose the best option for your application requirements. Dimensions Multi-Hub Design Resiliency · Independent scaling of DMZ and Core firewalls · Failure in Internet inspection does not impact East‑West traffic · Easier multi‑region active‑active designs Security & Compliance Clear trust boundaries Auditable inspection points Easier alignment with Zero Trust & regulatory frameworks Operational Simplicity Smaller, purpose‑built firewall policies Clear ownership (Perimeter vs Core team) Faster troubleshooting due to deterministic flows Cost Optimisation Avoids over‑inspection of East‑West traffic by DMZ firewalls Smaller firewall SKUs per hub Better scale‑unit consumption Performance Efficiency Reduced latency for private traffic No unnecessary hair‑pinning Optimised SNAT and connection tracking Key Takeaways Security‑first landing zones should not be designed as one‑size‑fits‑all networks. By designing hubs based on traffic trust level and inspection intent, rather than convenience, organisations gain: o Stronger security boundaries and better fault isolation o Predictable operations at scale o Lower long‑term cost and complexity o Design for traffic flows, not just connectivity o Use DMZ hubs exclusively for Internet‑untrusted traffic o Use Core hubs for East‑West, outbound, and hybrid connectivity o Map security controls to OSI layers o Avoid single‑hub designs for large, regulated, or multi‑region environments This distributed hub‑and‑DMZ landing zone provides a clean, scalable, and secure foundation for enterprise workloads in any hyperscaler. For regulated, internet‑exposed, or multi‑region environments, a distributed hub with a dedicated DMZ is no longer optional — it is a foundational architecture decision.How Azure network security can help you meet NIS2 compliance
With the adoption of the NIS2 Directive EU 2022 2555, cybersecurity obligations for both public and private sector organizations have become more strict and far reaching. NIS2 aims to establish a higher common level of cybersecurity across the European Union by enforcing stronger requirements on risk management, incident reporting, supply chain protection, and governance. If your organization runs on Microsoft Azure, you already have powerful services to support your NIS2 journey. In particular Azure network security products such as Azure Firewall, Azure Web Application Firewall WAF, and Azure DDoS Protection provide foundational controls. The key is to configure and operate them in a way that aligns with the directive’s expectations. Important note This article is a technical guide based on the NIS2 Directive EU 2022 2555 and Microsoft product documentation. It is not legal advice. For formal interpretations, consult your legal or regulatory experts. What is NIS2? NIS2 replaces the original NIS Directive 2016 and entered into force on 16 January 2023. Member states must transpose it into national law by 17 October 2024. Its goals are to: Expand the scope of covered entities essential and important entities Harmonize cybersecurity standards across member states Introduce stricter supervisory and enforcement measures Strengthen supply chain security and reporting obligations Key provisions include: Article 20 management responsibility and governance Article 21 cybersecurity risk management measures Article 23 incident notification obligations These articles require organizations to implement technical, operational, and organizational measures to manage risks, respond to incidents, and ensure leadership accountability. Where Azure network security fits The table below maps common NIS2 focus areas to Azure network security capabilities and how they support compliance outcomes. NIS2 focus area Azure services and capabilities How this supports compliance Incident handling and detection Azure Firewall Premium IDPS and TLS inspection, Threat Intelligence mode, Azure WAF managed rule sets and custom rules, Azure DDoS Protection, Azure Bastion diagnostic logs Detect, block, and log threats across layers three to seven. Provide telemetry for triage and enable response workflows that are auditable. Business continuity and resilience Azure Firewall availability zones and autoscale, Azure Front Door or Application Gateway WAF with zone redundant deployments, Azure Monitor with Log Analytics, Traffic Manager or Front Door for failover Improve service availability and provide data for resilience reviews and disaster recovery scenarios. Access control and segmentation Azure Firewall policy with DNAT, network, and application rules, NSGs and ASGs, Azure Bastion for browser based RDP SSH without public IPs, Private Link Enforce segmentation and isolation of critical assets. Support Zero Trust and least privilege for inbound and egress. Vulnerability and misconfiguration defense Azure WAF Microsoft managed rule set based on OWASP CRS. Azure Firewall Premium IDPS signatures Reduce exposure to common web exploits and misconfigurations for public facing apps and APIs. Encryption and secure communications TLS policy: Application Gateway SSL policy; Front Door TLS policy; App Service/PaaS minimum TLS. Inspection: Azure Firewall Premium TLS inspection Inspect and enforce encrypted communication policies and block traffic that violates TLS requirements. Inspect decrypted traffic for threats. Incident reporting and evidence Azure Network Security diagnostics, Log Analytics, Microsoft Sentinel incidents, workbooks, and playbooks Capture and retain telemetry. Correlate events, create incident timelines, and export reports to meet regulator timelines. NIS2 articles in practice Article 21 cybersecurity risk management measures Azure network controls contribute to several required measures: Prevention and detection. Azure Firewall blocks unauthorized access and inspects traffic with IDPS. Azure DDoS Protection mitigates volumetric and protocol attacks. Azure WAF prevents common web exploits based on OWASP guidance. Logging and monitoring. Azure Firewall, WAF, DDoS, and Bastion resources produce detailed resource logs and metrics in Azure Monitor. Ingest these into Microsoft Sentinel for correlation, analytics rules, and automation. Control of encrypted communications. Azure Firewall Premium provides TLS inspection to reveal malicious payloads inside encrypted sessions. Supply chain and service provider management. Use Azure Policy and Defender for Cloud to continuously assess configuration and require approved network security baselines across subscriptions and landing zones. Article 23 incident notification Build an evidence friendly workflow with Sentinel: Early warning within twenty four hours. Use Sentinel analytics rules on Firewall, WAF, DDoS, and Bastion logs to generate incidents and trigger playbooks that assemble an initial advisory. Incident notification within seventy two hours. Enrich the incident with additional context such as mitigation actions from DDoS, Firewall and WAF. Final report within one month. Produce a summary that includes root cause, impact, and corrective actions. Use Workbooks to export charts and tables that back up your narrative. Article 20 governance and accountability Management accountability. Track policy compliance with Azure Policy initiatives for Firewall, DDoS and WAF. Use exemptions rarely and record justification. Centralized visibility. Defender for Cloud’s network security posture views and recommendations give executives and owners a quick view of exposure and misconfigurations. Change control and drift prevention. Manage Firewall, WAF, and DDoS through Network Security Hub and Infrastructure as Code with Bicep or Terraform. Require pull requests and approvals to enforce four eyes on changes. Network security baseline Use this blueprint as a starting point. Adapt to your landing zone architecture and regulator guidance. Topology and control plane Hub and spoke architecture with a centralized Azure Firewall Premium in the hub. Enable availability zones. Deploy Azure Bastion Premium in the hub or a dedicated management VNet; peer to spokes. Remove public IPs from management NICs and disable public RDP SSH on VMs. Use Network Security Hub for at-scale management. Require Infrastructure as Code for all network security resources. Web application protection Protect public apps with Azure Front Door Premium WAF where edge inspection is required. Use Application Gateway WAF v2 for regional scenarios. Enable the Microsoft managed rule set and the latest version. Add custom rules for geo based allow or deny and bot management. enable rate limiting when appropriate. DDoS strategy Enable DDoS Network Protection on virtual networks that contain internet facing resources. Use IP Protection for single public IP scenarios. Configure DDoS diagnostics and alerts. Stream to Sentinel. Define runbooks for escalation and service team engagement. Firewall policy Enable IDPS in alert and then in alert and deny for high confidence signatures. Enable TLS inspection for outbound and inbound where supported. Enforce FQDN and URL filtering for egress. Require explicit allow lists for critical segments. Deny inbound RDP SSH from the internet. Allow management traffic only from Bastion subnets or approved management jump segments. Logging, retention, and access Turn on diagnostic settings for Firewall, WAF, DDoS, and Application Gateway or Front Door. Send to Log Analytics and an archive storage account for long term retention. Set retention per national law and internal policy. Azure Monitor Log Analytics supports table-level retention and archive for up to 12 years, many teams keep a shorter interactive window and multi-year archive for audits. Restrict access with Azure RBAC and Customer Managed Keys where applicable. Automation and playbooks Build Sentinel playbooks for regulator notifications, ticket creation, and evidence collection. Maintain dry run versions for exercises. Add analytics for Bastion session starts to sensitive VMs, excessive failed connection attempts, and out of hours access. Conclusion Azure network security services provide the technical controls most organizations need in order to align with NIS2. When combined with policy enforcement, centralized logging, and automated detection and response, they create a defensible and auditable posture. Focus on layered protection, secure connectivity, and real time response so that you can reduce exposure to evolving threats, accelerate incident response, and meet NIS2 obligations with confidence. References NIS2 primary source Directive (EU) 2022/2555 (NIS2). https://eur-lex.europa.eu/eli/dir/2022/2555/oj/eng Azure Firewall Premium features (TLS inspection, IDPS, URL filtering). https://learn.microsoft.com/en-us/azure/firewall/premium-features Deploy & configure Azure Firewall Premium. https://learn.microsoft.com/en-us/azure/firewall/premium-deploy IDPS signature categories reference. https://learn.microsoft.com/en-us/azure/firewall/idps-signature-categories Monitoring & diagnostic logs reference. https://learn.microsoft.com/en-us/azure/firewall/monitor-firewall-reference Web Application Firewall WAF on Azure Front Door overview & features. https://learn.microsoft.com/en-us/azure/frontdoor/web-application-firewall WAF on Application Gateway overview. https://learn.microsoft.com/en-us/azure/web-application-firewall/overview Examine WAF logs with Log Analytics. https://learn.microsoft.com/en-us/azure/application-gateway/log-analytics Rate limiting with Front Door WAF. https://learn.microsoft.com/en-us/azure/web-application-firewall/afds/waf-front-door-rate-limit Azure DDoS Protection Service overview & SKUs (Network Protection, IP Protection). https://learn.microsoft.com/en-us/azure/ddos-protection/ddos-protection-overview Quickstart: Enable DDoS IP Protection. https://learn.microsoft.com/en-us/azure/ddos-protection/manage-ddos-ip-protection-portal View DDoS diagnostic logs (Notifications, Mitigation Reports/Flows). https://learn.microsoft.com/en-us/azure/ddos-protection/ddos-view-diagnostic-logs Azure Bastion Azure Bastion overview and SKUs. https://learn.microsoft.com/en-us/azure/bastion/bastion-overview Deploy and configure Azure Bastion. https://learn.microsoft.com/en-us/azure/bastion/tutorial-create-host-portal Disable public RDP and SSH on Azure VMs. https://learn.microsoft.com/en-us/azure/virtual-machines/security-baseline Azure Bastion diagnostic logs and metrics. https://learn.microsoft.com/en-us/azure/bastion/bastion-diagnostic-logs Microsoft Sentinel Sentinel documentation (onboard, analytics, automation). https://learn.microsoft.com/en-us/azure/sentinel/ Azure Firewall solution for Microsoft Sentinel. https://learn.microsoft.com/en-us/azure/firewall/firewall-sentinel-overview Use Microsoft Sentinel with Azure WAF. https://learn.microsoft.com/en-us/azure/web-application-firewall/waf-sentinel Architecture & routing Hub‑spoke network topology (reference). https://learn.microsoft.com/en-us/azure/architecture/networking/architecture/hub-spoke Azure Firewall Manager & secured virtual hub. https://learn.microsoft.com/en-us/azure/firewall-manager/secured-virtual-hub
Azure DDoS Protection & Azure WAF: A Layered Defense for Modern DDoS Attacks
Introduction: The Need for Layered DDoS Defense Organizations today operate in an environment where Distributed Denial of Service (DDoS) attacks continue to evolve across both network and application layers. To help organizations build resilient, internet-facing applications and services, Microsoft Azure provides a comprehensive and layered set of protections designed to address different types of DDoS threats. These capabilities range from platform-level defenses through Azure Infrastructure Protection, dedicated Layer 3/4 DDoS mitigation through Azure DDOS Protection and application-layer protections through Azure Web Application Protection (WAF). Together, these services form a defense-in-depth strategy that helps organizations strengthen availability, improve resilience, and protect critical applications from both large-scale network attacks and sophisticated application-layer threats. This blog explores how these services work together to deliver comprehensive DDoS protection across modern cloud environments. Understanding DDoS at Different Layers: Network vs. Application Not all DDoS attacks are alike. Broadly speaking, network-layer (Layer 3/4) DDoS attacks try to flood a network or transport layer with traffic – for example, overwhelming a server or network connection with a massive volume of packets (think UDP floods, SYN floods, or amplification attacks). These aim to saturate the available bandwidth or crash network devices, knocking entire services offline. On the other hand, application-layer (Layer 7) DDoS attacks strike at the application itself – typically using HTTP(S) requests that appear legitimate but are maliciously crafted. For instance, a botnet might repeatedly hit a search API or login page with valid-looking requests that each trigger expensive operations (database queries, authentication processes, etc.). In short, network-layer DDoS attacks target the plumbing of your infrastructure (bandwidth, network connectivity), whereas application-layer DDoS attacks target the brains of your application (the code and logic handling requests). Because these attack vectors are different, defending against them requires different tools and tactics. Azure’s approach to DDoS defense embraces this reality with a layered model, where each security layer specializes in stopping certain types of attacks and complements the others. Azure’s multi-layered DDoS Protection Strategy Azure provides three main layers of DDoS protection: Azure’s Infrastructure DDoS Protection (Platform Protection) Azure DDoS Protection (Network Protection for customers’ resources) Azure Web Application Firewall (WAF) (App Protection) Let’s explore each layer and how they work together. Azure DDoS Infrastructure Protection (Always-On Baseline) All of the Azure Platform and shared services, automatically benefit from Azure’s built-in DDoS infrastructure protection. Think of this as Azure’s global, always-on “baseline” DDoS defense. It continuously monitors traffic across the Azure network, and if a massive DDoS campaign tries to bring down Azure’s infrastructure or a customer’s public endpoint, Azure will detect and absorb the malicious traffic at the platform level. This baseline protection uses Azure’s global network capacity to scrub much of the unwanted traffic before it ever reaches your resources. There’s no extra cost or configuration needed for this default protection. It’s a fundamental safety net that ensures Azure services (including multi-tenant services like Azure DNS) are not easily taken offline by large-scale DDoS events. However, the platform-level protection is designed primarily to protect Azure’s overall infrastructure and does not provide fine-grained controls or visibility for individual customers. That’s where Azure’s next layer comes in. Azure DDoS Protection: Shielding the Network (L3/L4) To safeguard your own internet-facing resources and workloads against network-layer DDoS attacks beyond the default baseline, Azure offers L3/L4 DDoS Protection (DDoS Network Protection and DDoS IP Protection) against volumetric floods. This is an opt-in service you configure for your Virtual Network or specific Public IP resources. Azure DDoS Protection is purpose-built to handle the classic L3/L4 DDoS scenarios: large volumetric floods, protocol attacks, and other network-level exploits like reflection or amplification attacks. A key benefit of Azure DDoS Protection is its adaptive tuning feature alongside the telemetry it provides. During peacetime, the service establishes a baseline of normal traffic behavior for your services and continuously updates that baseline to reflect changing patterns. When traffic deviates from that baseline and an attack is detected, mitigation is triggered automatically to block or absorb malicious traffic while minimizing false positives. Another important aspect of Azure DDoS Protection is visibility and response capabilities. The service provides detailed metrics, alerts, and attack analytics during and after an event, so your teams can understand what happened. Azure DDoS Network Protection plan also includes support from Azure’s DDoS Rapid Response (DRR) team and offers a cost protection guarantee – credits to offset any unexpected Azure scale-out costs that result from a documented DDoS attack. In short, Azure DDoS Protection is your dedicated shield at the network layer. It's worthwhile to note that Azure DDOS Protection goes beyond just blunt filtering; it employs multiple mitigation techniques like dropping illegitimate packets (for instance, filtering out spoofed source IPs or malformed packets), DDoS booters (e.g. DDoS-for-hire services), protocol compliance checks, and intelligent rate limiting as a last resort. It further employs multiple policies with varied thresholds each for UDP, TCP and TCP SYN due to the nature of attacks for these protocols. The goal is to scrub out the attack traffic while letting legitimate users continue to reach your services with minimal disruption. Azure WAF: Guarding Applications at the HTTP Layer (L7) Azure DDoS Protection defends against network-level floods and protocol exploits, but application-layer attacks like HTTP request floods require separate L7 protection with WAF. Azure WAF is deployed on services like Azure Application Gateway, Azure Front Door and Azure Gateway for Containers to inspect incoming HTTP(S) requests to your web applications. WAF’s primary role is to block common web exploits (e.g., SQL injections, cross-site scripting) via managed rule sets, rate Limit traffic using its Custom Rules as well as providing protection from malicious bots using its Bot Ruleset. Now, Azure WAF also includes the HTTP DDOS Ruleset to protect against application-level DDoS attacks. HTTP DDOS Ruleset is a new adaptive ruleset (currently in public preview for Application Gateway and Front Door services) that uses machine learning to dynamically learn normal HTTP traffic patterns for your application and automatically identify unusual surges in requests. If a burst of traffic appears malicious (for example, a sudden wave of requests to an expensive API call), the WAF can selectively block offending clients by placing them in a temporary “penalty box” without manual intervention. This dynamic approach goes beyond static thresholds, adjusting to your app’s normal load profiles. Along with that, adding the existing approaches such as custom rate limiting that lets you define granular thresholds for incoming requests on specific paths or for specific clients will further enhance the protection against DDOS attacks. For instance, you might limit a single IP to a certain number of login attempts per minute or cap the request rate to an expensive search endpoint. Rate limiting ensures that even if an attacker tries to slowly overwhelm your application with a moderate stream of requests (under the radar of network DDoS detection), WAF can throttle or block them at the application entry point. JavaScript challenges and CAPTCHA-based validation can also serve as effective protection mechanisms against automated bot traffic. These techniques help distinguish legitimate users from non-human clients by requiring the requester to successfully execute browser-based checks or complete a human verification step, making them useful for reducing unwanted bot activity such as scraping, credential stuffing, and abusive request automation. Further, the Bot Protection ruleset that includes integration of Microsoft’s threat intelligence to identify known malicious bot networks automatically block bad bots. Microsoft Threat Intelligence feeds continuously update the list of dangerous bot IPs and prevents these bots from consuming your application’s resources. This is especially useful against DDoS scenarios carried out by automated botnets that have known fingerprints. Together these capabilities enable Azure WAF to act as a critical inner layer of DDoS defense in front of your applications (via an Application Gateway or Front Door). Azure WAF focuses on application-specific attacks, and it can discern whether a burst of requests to your app is likely malicious based on patterns and behavior, not just volume. Combined with network-level DDoS protection, WAF ensures that even low-bandwidth but high-impact attacks (like repeated login attempts or bot-driven scraping) are mitigated. Layered DDOS Protection: Azure’s DDoS strategy is best imagined as a series of concentric rings around your application. The outermost ring is the platform’s infrastructure DDoS protection (automatically absorbing massive network floods aimed at Azure at large). The next ring is Azure DDoS Protection for your environment, which provides dedicated L3/L4 defenses with tuning and telemetry – it will handle the heavy lifting against volumetric and protocol attacks targeted at your specific resources. The next ring inward is your Azure WAF (with its HTTP DDoS ruleset, rate limiting, and bot controls enabled) catching the application-layer anomalies that network defenses can’t see. And finally, the innermost ring might be endpoint-specific configurations or app-level controls (like strict rate limits on crucial API operations or even adaptive app logic) that protect the most sensitive parts of your application from abuse. This layered approach is essential. Each layer addresses different threat vectors and failure modes; together they fill the gaps and provide a robust, end-to-end DDoS mitigation strategy. Quick Comparison: Azure DDoS Protection vs Azure WAF Note: This comparison focuses on Azure DDoS Protection and Azure WAF because they are the paid offerings; Azure DDoS Infrastructure Protection is included by default. To crystallize the differences and synergy between these services, here’s a quick side-by-side comparison of Azure DDoS Protection (Network level) and Azure WAF (Application level) in the context of DDoS defense: Service Azure DDoS Protection (Network-Level) Azure WAF – Application (Layer 7) DDoS Protection Protection Layer Network (OSI Layers 3 & 4): Protects Internet facing resources in virtual networks. Application (OSI Layer 7): Protects web apps and APIs at the HTTP request layer. Protected Resource Internet facing resources in virtual networks. Web apps and API endpoints. Primary Purpose Shield against high-volume network floods (e.g. UDP/TCP floods, SYN floods, amplification attacks) that aim to overwhelm bandwidth or network resources. Ensures your Azure services stay reachable during massive DDoS assaults. Filter and stop malicious HTTP(S) traffic (e.g. HTTP GET/POST floods, bot-driven requests, slowloris attacks) that could exhaust your application’s compute resources. Keeps your web applications responsive even under targeted L7 attack patterns. How It Works Always-on network monitoring. Uses Azure’s global network to absorb and scrub malicious traffic before it reaches your resources. No per-app manual tuning needed – it profiles traffic and triggers mitigation when volumes exceed safe baselines. Employs adaptive techniques (drops spoofed packets, protocol checks, limits rate as last resort) to block attacks while letting legitimate traffic flow. Policy-driven rules integrated at the application edge (via Application Gateway or Front Door). Can rate-limit or block suspicious clients based on IP, behavior, or patterns. Includes managed rule sets for common web threats and a new adaptive HTTP DDoS managed ruleset that auto-learns normal behavior per app and blocks abnormal request surges (reducing need for manual emergency configuration). When to Use Ideal for any Azure resource exposed to the public internet. Especially critical for high-bandwidth endpoints (gaming servers, large websites, etc.) or anything that can’t risk downtime due to massive traffic floods. Typically enabled on Virtual Networks or specific public IP addresses. Essential for any internet-facing web application (websites, web services, REST APIs). Particularly important for applications with resource-intensive operations (e.g., login pages, search functionality) where even moderate traffic spikes can degrade service. Deployed via a WAF Policy on an Application Gateway or Front Door that fronts your app. Role in Defense-in-Depth Handles the “heavy lifting” against bulk traffic attacks at the network edge – drastically reduces attacking traffic volume before it can hit your servers. Prevents upstream network pipe saturation or crashes, ensuring your application gets a chance to handle legitimate user traffic. Provides a fine-grained, application-aware filter for attacks that get past network defenses. Targets “surgical” low-bandwidth attacks that hide within normal traffic patterns. Together with Azure DDoS Protection, WAF completes a full-stack DDoS defense, covering gaps that pure network protection would miss. Conclusion: The key takeaway is that modern DDoS defense is no longer about relying on a single control, but about applying defense-in-depth, the right protection at the right layer. With a layered approach that spans infrastructure, network, and application security, organizations are better positioned to preserve availability, protect user experience, and maintain business continuity even as DDoS attacks grow more sophisticated.Azure WAF Tuning for Web Applications
False positives occur when a Web Application Firewall (WAF) erroneously detects legitimate web traffic as malicious and subsequently denies access. For instance, an HTTP request that poses no threat may trigger WAF to classify it as an SQL injection attack due to how characters are passed through the request body, thereby causing the request to be rejected and denying access to the user. Find out in this post some examples to help reduce false positives in your Azure WAF environment.General availability of Default Ruleset (DRS) 2.2 for Web Application Firewall
Introduction As attackers continue to evolve their techniques, organizations require web application security that keeps pace with emerging threats without disrupting legitimate traffic. Azure Web Application Firewall (WAF) continues to evolve to meet these demands and now supports Default Rule Set (DRS) 2.2 across both Azure Front Door and Azure Application Gateway. The latest recommended Azure WAF ruleset, based on OWASP Core Rule Set (CRS) 3.3.4., DRS 2.2 combines OWASP CRS protections with Microsoft-authored rules developed with the Microsoft Threat Intelligence team, delivering broader coverage, updated signatures, reduced false positives, and a more modern security baseline for your internet-facing applications. What is new in DRS 2.2? DRS 2.2 builds on earlier rule sets with improvements focused on three areas: breadth of coverage, quality of detections, and false positive reductions. Broader security coverage DRS 2.2 is based on the OWASP Core Rule Set 3.3.4, delivering improvements in rule accuracy and new protections for common web vulnerabilities. DRS 2.2 contains 18 rule groups, organizing protections across SQL injections, XSS, protocol violations, remote code execution, and more, making it easier to understand and manage the scope of coverage. Notable improvements include: Detection of mismatched content types, where the declared content-type header does not match the actual payload format. This is a common tactic in evasion and obfuscation attacks. Improved Remote Code Execution (RCE) detections to catch increasingly sophisticated payloads used by threat actors. Microsoft Threat Intelligence rules In addition to the OWASP improvements, DRS 2.2 introduces new Microsoft Threat Intelligence rules. These rules expand coverage for: SQL Injection. Cross-Site Scripting (XSS). Advanced application security attack patterns. Improved false positive reduction with paranoia levels One of the standout features of DRS 2.2 is its paranoia level (PL) configuration, which allows you to balance security and usability. Paranoia levels (PL) determine how aggressively rules in the OWASP Core Rule Set (CRS) detect and block potential threats in a Web Application Firewall (WAF). OWASP CRS defines four paranoia levels (PL1–PL4), each offering progressively stricter security controls: PL1 (Default): Offers baseline protection against common web attacks, minimizes false positives, and is appropriate for most applications. PL2: Adds additional rules targeting more sophisticated threats, which may result in more false positives. PL3: Strict detection rules aimed at high-security environments. PL4: Implements the most aggressive security rules, suitable for highly secure environments, requiring extensive management and tuning efforts. Azure WAF currently does not support rules from paranoia levels 3 and 4. For more information on Azure WAF paranoia levels refer to Paranoia Levels. DRS 2.2 ships with paranoia level 1 (PL1) enabled by default. This gives customers the strongest baseline protection with minimal tuning overhead. DRS 2.2 rules configured in paranoia level 2 are disabled by default. Customers can leave PL2 disabled or selectively enable individual PL2 rules based on their threat model and application behavior. Enabling and upgrading to DRS 2.2 Upgrading to DRS 2.2 is straightforward, but there is an important planning consideration: when you assign a new managed ruleset version through the Azure portal, previous managed-ruleset customizations such as rule state overrides, rule action overrides, and rule-level exclusions are reset to the new defaults. Due to this, it is recommended to use PowerShell, CLI, REST API, or templates when you want to preserve overrides and exclusions, and validating changes in a test environment before production rollout. Please refer to Upgrade CRS or DRS Ruleset Version - Azure Web Application Firewall. To use DRS 2.2: Open your WAF policy (associated with your Azure Front Door or Application Gateway). Navigate to Managed Rules. Select “Assign”. Choose DRS 2.2 from the ruleset dropdown. Review enabled rule groups and optionally configure the rule actions. After upgrading, monitor your logs and metrics to understand traffic behavior and fine-tune as required. Figure 1: Enabling DRS 2.2 in Azure Front Door WAF Figure 2: Enabling DRS 2.2 in Azure Front Door WAF Conclusion Default Rule Set 2.2 marks a significant advancement for Azure Web Application Firewall, providing stronger security coverage, improved detection accuracy, and better control over false positives. By bringing the same modern ruleset experience to both Azure Front Door WAF and Application Gateway WAF, customers can apply a consistent web security baseline across global, regional, and internal application architectures. For customers already using Azure WAF, upgrading to DRS 2.2 is the simplest way to benefit from the latest protections while maintaining operational flexibility. References Web Application Firewall (WAF) on Azure Front Door | Microsoft Learn Web Application Firewall on Azure Application Gateway | Microsoft Learn Azure Front Door WAF - DRS and CRS rule groups and rules | Microsoft Learn Azure Application Gateway WAF - DRS and CRS rule groups and rules Azure Front Door WAF - Default Ruleset 2.2 | Microsoft Learn Application Gateway WAF – Default Ruleset 2.2 | Microsoft Learn Upgrade CRS or DRS Ruleset Version - Azure Web Application Firewall | Microsoft LearnZero Trust with Azure Firewall, Azure DDoS Protection and Azure WAF: A practical use case
Introduction Zero Trust has emerged as the defining security ethos of the modern enterprise. It is guided by a simple but powerful principle: “Never trust, always verify.” This principle is more relevant now than ever as cyberattacks continue to trend upward in both frequency and impact, affecting organizations of every size and industry. No entity large or small can assume immunity. As a result, adopting Zero Trust is no longer optional, it is a foundational requirement for designing secure, resilient architectures. A key tenet of Zero Trust is the assumption of breach, thus designing systems with the expectation that threats may already exist both outside and inside the network perimeter. To implement this principle, you need multiple, independent security controls that inspect traffic at different layers and enforce least privilege access continuously. Relying on a single security control, even a highly capable one, leaves gaps that modern attackers are adept at exploiting. It is within this context that combining the use of Azure Firewall, Azure DDoS Protection and Azure Web Application Firewall (WAF) services to secure Web Applications while protecting the network perimeter becomes important. Together, these services deliver comprehensive protection across the network and application layers. Defense-in-depth: Why Azure WAF, Azure DDoS Protection and Azure Firewall are essential for Zero Trust In these sections ahead, we examine the common network and application-layer attack vectors that target modern web applications and illustrate how Azure WAF, Azure DDoS protection, and Azure Firewall, when layered strategically, work in tandem to mitigate these threats. The architecture The test environment was designed to reflect a common Azure deployment pattern: Azure DDoS Protection at the edge, to defend against a comprehensive set of network layer (layer 3/4) attacks Azure Application Gateway with WAF, inspecting inbound HTTP traffic for application-layer threats Azure Firewall Premium behind the gateway, providing network-layer protection, deep packet inspection, and outbound traffic governance. A backend subnet hosting an intentionally vulnerable application (OWASP Juice Shop) to simulate real-world attack scenarios. Traffic flows through the DDoS first, then WAF, and then the firewall, before reaching the backend. Outbound traffic from the backend is routed through the firewall for inspection. This ensures that all inbound and outbound traffic is scrutinized. Two access paths that will be tested: Via the Application Gateway public IP, where traffic passes through DDoS, WAF and Firewall. Via the Firewall public IP using a DNAT rule, where traffic bypasses WAF and is inspected only by the Firewall. The following scenarios illustrate how this complementary protection strengthens overall resilience: Scenario 1: SQL injection (application-layer attack) Let’s say an attacker on the internet attempts to access the application’s login endpoint via the Application Gateway IP address and injects a SQL payload into the input field. For example, the attacker submits a request containing the following payload in the User ID field: ?id=' OR 1=1 -- Azure WAF will receive the request, analyze, and if Azure WAF is deployed in Prevention mode, it will immediately detect the SQL injection attempt using its built-in Managed Ruleset. Upon detection, Azure WAF will return a WAF block page, preventing the request from ever reaching the application. By contrast, when the same application is accessed through a firewall-only path (for example, via a DNAT rule on Azure Firewall that exposes the application on port 443), Azure Firewall allows the traffic as it does not perform deep Application layer inspection and SQL injection payloads when embedded within the HTTP request body, appear legitimate at the network layer. Here is a snapshot of the attacker gaining access to the admin role when they insert this SQL injection attack without Azure WAF and only Azure Firewall in the path. Scenario 2: Volumetric and application-layer DDoS attacks Next, the attacker launches a volumetric network layer DDoS (SYN/UDP floods) to saturate bandwidth, but Azure DDoS Network Protection absorbs and scrubs the attack at the edge, so no traffic reaches Application Gateway, WAF, or Firewall. When the network layer attack fails, they shift to HTTP flood attack at the application layer, overwhelming the web application with a high volume of requests. Some requests include exploit attempts, while others are designed purely to exhaust application resources. Azure WAF here, can identify malicious patterns such as: Automated bots lacking proper headers Abnormal request rates Known exploit payloads embedded within requests Malicious IP addresses Note: Azure DDoS Protection is a comprehensive service that provides protection across network layers (Layer 3 and 4), while HTTP DDoS Protection specifically targets application-layer attacks (Layer 7) and is integrated with Azure WAF. They are complementary services designed to defend against different types of threats within the Azure environment. Additionally, if the botnet’s IPs are known threat actors or malicious traffic, Azure Firewall’s threat intelligence and IDPS will be able to flag this traffic too. Together, these services form a complementary, defense-in-depth strategy for protecting Azure workloads against distributed denial-of-service attacks. Scenario 3: Path Traversal Attempt/Information leak: (Application-Layer Attack) Next, the attacker sends HTTP requests to access sensitive system files such as /etc/passwd by sending crafted HTTP requests to the application via the Application Gateway public IP address. The request successfully passes through Azure Application Gateway WAF, as it does not trigger a managed rule violation in this case. However, when the request reaches Azure Firewall, the Firewall’s IDPS detects the malicious pattern in the HTTP header and blocks the connection before it can reach the backend workload. Because the backend connection is denied by Azure Firewall, Application Gateway is unable to establish a successful response and returns a 504 Gateway Timeout to the client, rather than a 403 Forbidden response that would typically be generated by WAF when it blocks traffic. Below is the log from Azure Firewall showing that its able to detect this traffic as – Attempted Information Leak. As seen below, the traffic passed Application Gateway+WAF but was caught by Azure Firewall: This scenario highlights an important architectural outcome: The combination of WAF and Azure Firewall provides layered enforcement, even if an attack manages to slip past Azure WAF, Azure Firewall adds an additional enforcement layer to ensure the application remains protected. Now, let’s look at some more Network Layer attacks: Scenario 4: Network reconnaissance and breach In this scenario, port 3389 is exposed on Application Gateway using the L4 TCP Proxy option. Now, the attacker attempts to scan the Application Gateway on all the ports/protocols and found that port 3389 was open along with other ports such as ports 80, 8080, 3000. Azure WAF will alert us for Layer 7/Application exploit but cannot verify/validate the attack on port 3389 since it was purely Layer 3/4 and contained no HTTP payload for WAF inspection. The L4 proxy listener on App Gateway simply forwards the raw TCP connections to the Azure Firewall behind it. Azure Firewall, however, performs full network‑layer inspection across all ports and protocols, allowing it to detect and alert on this type of L3/L4 reconnaissance even when App Gateway had the port open via the TCP proxy feature. As seen below the traffic passed Application Gateway+WAF but was caught by Azure Firewall since it is non-HTTP: The attacker then tries a different approach: Now the attacker somehow compromises a workstation inside our network and attempts to move laterally to the web server via RDP on port 3389 and/or attempts to exfiltrate and try to access something outside of the network. Azure Firewall located inside the VNet blocks the RDP attempt (if there is no rule allowing it) and if there is, its IDPS flags/blocks the traffic as suspicious. In this case, Azure WAF will not be involved but Azure Firewall inspects this internal and/or outbound traffic and blocks it. This illustrates how a combination of the two stops the attacker at multiple points: firewall foiled the reconnaissance and lateral movement/exfiltration, WAF foiled the application exploit. We can see below the outbound malicious attempt caught by Azure Firewall IDPS: In summary, Azure WAF is like the “bodyguard at the application’s front door” – inspecting every HTTP request in detail and ejecting those carrying hidden weapons or exhibiting bad behavior. It focuses on the web layer, which Azure Firewall or DDoS alone cannot fully protect. If we only had the WAF and no network firewall or DDoS, we’d be safe from many web attacks but would remain exposed to network-level threats (e.g., someone trying to RDP into a VM, or flooding a non-HTTP service). Conversely, if we had only the firewall, a crafty attacker could still exploit a vulnerability in our web app with a well-crafted HTTP request that looks “allowed” to the firewall – that’s where the WAF comes in to catch it. Azure Firewall on the other hand, acts as the “moat and drawbridge” to your cloud network: it keeps out the obvious bad guys at the gate, tightly limits what’s allowed in or out (no implicit trust for internal IPs), and uses threat intel + signatures to sniff out known threats in any traffic it passes, even outbound traffic. The table below shows the traffic flow that will be filtered by Azure WAF vs Azure Firewall. As you can see, layered security is fundamental to Zero Trust Conclusion In a Zero Trust architecture, security cannot rely on implicit trust or a single layer of defense. The combination of Azure Firewall Premium, Azure DDoS protection and Azure Application Gateway WAF exemplifies defense-in-depth by protecting both network and application layers. Organizations hosting internet-facing applications should adopt this layered strategy to reduce exposure to modern threats, prevent lateral movement, and maintain strict control over outbound traffic. By implementing these services together, you align with Microsoft’s recommended best practices for Zero Trust and significantly strengthen your cloud security posture. References: Implement a Zero Trust network for web applications by using Azure Firewall and Azure Application Gateway What is Azure Web Application Firewall? Azure DDoS Protection Overview | Microsoft Learn What is Azure Firewall? Architecture designs using Azure WAF and Azure Firewall together Zero Trust Assessment Overview | Microsoft Learn
Protect against React RSC CVE-2025-55182 with Azure Web Application Firewall (WAF)
Please subscribe to this blog as we will be updating the suggested rules as new attack permutations are found. On December 3, 2025, the React team disclosed a critical remote code execution (RCE) vulnerability in React Server Components (RSC), tracked as CVE-2025-55182. The vulnerability allows an unauthenticated attacker to send a specially crafted request to an RSC “Server Function” endpoint and potentially execute arbitrary code on the server. This vulnerability affects applications using React RSC in the following versions: 19.0.0 19.1.0 19.1.1 19.2.0 Patched versions are available, and all customers are strongly encouraged to update immediately. About CVE-2025-55182 According to the React security advisory, the issue stems from unsafe deserialization within React Server Components, where server function payloads were not adequately validated. When exploited, an attacker can execute arbitrary code on the server without authentication. The NVD entry classifies this vulnerability as Critical, with a CVSS score of 10.0, due to its ease of exploitation and the potential impact on server-side execution. All organizations using React Server Components — or frameworks that embed RSC capabilities such as Next.js, React Router (RSC mode), Waku, @parcel/rsc, @vitejs/plugin-rsc, or rwsdk — should consider themselves potentially exposed until the relevant patches are applied. Azure WAF Mitigation to CVE-2025-55182 The primary and most effective mitigation for this vulnerability is to upgrade any unpatched React versions to the latest security-patched releases. Mitigation on WAF on Application Gateway or Application Gateway for Containers If you are using the latest and recommended Default Rule Set (DRS) 2.1, or the previous Core Rule Set (CRS) 3.2, a new CVE-specific managed rule is available in Azure Web Application Firewall (WAF) for Application Gateway and Application Gateway for Containers. Please ensure this rule is enabled and retains its default Anomaly Score–based action: Rule ID: 99001018 (DRS 2.1) or 800115 (CRS 3.2) Rule description: Attempted React2Shell remote code execution exploitation (CVE-2025-55182) This CVE-specific rule has also been added to CRS 3.1. However, for enhanced and more comprehensive protection specifically against CVE-2025-55182, we strongly recommend upgrading to DRS 2.1, which includes additional detection coverage and tuning for this vulnerability. If you are using CRS 3.0, there is no built-in CVE-specific protection for CVE-2025-55182, and upgrading to DRS 2.1 is strongly advised. If upgrading is not currently possible, you may implement custom WAF rules to detect this exploit pattern using a Block action. Any custom rules should be validated in a test or staging environment before being enforced in production. Custom rules definition for WAF on Application Gateway and Application Gateway for Containers: "customRules": [ { "name": "cve202555182", "priority": 1, "ruleType": "MatchRule", "action": "Block", "matchConditions": [ { "matchVariables": [ { "variableName": "PostArgs" } ], "operator": "Contains", "negationConditon": false, "matchValues": [ "constructor", "__proto__", "prototype", "_response" ], "transforms": [ "Lowercase", "UrlDecode", "RemoveNulls" ] }, { "matchVariables": [ { "variableName": "RequestHeaders", "selector": "next-action" } ], "operator": "Any", "negationConditon": false, "matchValues": [], "transforms": [] } ], "skippedManagedRuleSets": [], "state": "Enabled" }, { "name": "cve202555182ver2", "priority": 100, "ruleType": "MatchRule", "action": "Block", "matchConditions": [ { "matchVariables": [ { "variableName": "PostArgs" } ], "operator": "Contains", "negationConditon": false, "matchValues": [ "constructor", "__proto__", "prototype", "_response" ], "transforms": [ "Lowercase", "UrlDecode", "RemoveNulls" ] }, { "matchVariables": [ { "variableName": "RequestHeaders", "selector": "rsc-action-id" } ], "operator": "Any", "negationConditon": false, "matchValues": [], "transforms": [] } ], "skippedManagedRuleSets": [], "state": "Enabled" } ], Adding these custom rules may fail if your WAF runs on the old WAF engine. In this case, we strongly recommend upgrading your WAF policy to the next-generation WAF engine by moving to a newer ruleset: either to the latest DRS 2.1 which includes the built-in managed rule (preferred) or to the previous CRS 3.2, then apply the custom rules described above. If upgrading your ruleset version is not an option, and your WAF remains on the old WAF engine, you can instead use the following alternative rules: "CustomRules": [ { "Name": "cve202555182", "Priority": 1, "RuleType": "MatchRule", "MatchConditions": [ { "MatchVariables": [ { "VariableName": "PostArgs" } ], "Operator": "Contains", "MatchValues": [ "constructor", "__proto__", "prototype", "_response" ], "Transforms": [ "Lowercase", "UrlDecode", "RemoveNulls" ] }, { "MatchVariables": [ { "VariableName": "RequestHeaders", "Selector": "next-action" } ], "Operator": "Regex", "MatchValues": [ "." ], "Transforms": [] } ], "Action": "Block" }, { "Name": "cve202555182ver2", "Priority": 2, "RuleType": "MatchRule", "MatchConditions": [ { "MatchVariables": [ { "VariableName": "PostArgs" } ], "Operator": "Contains", "MatchValues": [ "constructor", "__proto__", "prototype", "_response" ], "ATransforms": [ "Lowercase", "UrlDecode", "RemoveNulls" ] }, { "MatchVariables": [ { "VariableName": "RequestHeaders", "Selector": "rsc-action-id" } ], "Operator": "Regex", "MatchValues": [ "." ], "Transforms": [] } ], "Action": "Block" } ] Mitigation for WAF on Azure Front Door: If you are using WAF on Azure Front Door, you can create custom WAF rules to detect this exploit pattern. These custom rules are configured with a Block action. We recommend validating them in a test or staging environment before enforcing them in production. "customRules": [ { "name": "cve202555182", "enabledState": "Enabled", "priority": 1, "ruleType": "MatchRule", "rateLimitDurationInMinutes": 1, "rateLimitThreshold": 100, "matchConditions": [ { "matchVariable": "RequestHeader", "selector": "next-action", "operator": "Any", "negateCondition": false, "matchValue": [], "transforms": [] }, { "matchVariable": "RequestHeader", "selector": "content-type", "operator": "Contains", "negateCondition": false, "matchValue": [ "multipart/form-data", "application/x-www-form-urlencoded" ], "transforms": [ "Lowercase" ] }, { "matchVariable": "RequestBody", "operator": "Contains", "negateCondition": false, "matchValue": [ "constructor", "__proto__", "prototype", "_response" ], "transforms": [ "Lowercase", "UrlDecode", "RemoveNulls" ] } ], "action": "Block", "groupBy": [] }, { "name": "cve202555182ver2", "enabledState": "Enabled", "priority": 2, "ruleType": "MatchRule", "rateLimitDurationInMinutes": 1, "rateLimitThreshold": 100, "matchConditions": [ { "matchVariable": "RequestHeader", "selector": "rsc-action-id", "operator": "Any", "negateCondition": false, "matchValue": [], "transforms": [] }, { "matchVariable": "RequestHeader", "selector": "content-type", "operator": "Contains", "negateCondition": false, "matchValue": [ "multipart/form-data", "application/x-www-form-urlencoded" ], "transforms": [ "Lowercase" ] }, { "matchVariable": "RequestBody", "operator": "Contains", "negateCondition": false, "matchValue": [ "constructor", "__proto__", "prototype", "_response" ], "transforms": [ "Lowercase", "UrlDecode", "RemoveNulls" ] } ], "action": "Block", "groupBy": [] } ] You can find more information about Custom Rules on Azure WAF for Application Gateway here or for Azure Front Door here. Changelog 1/19/2026 5:00 PST - Updated built-in managed rule for CRS 3.2 and CRS 3.1 on WAF for Application Gateway 12/20/2025 11:00 PST - Updated built-in managed rule on WAF for Application Gateway and Application Gateway for Containers 12/7/2025 23:30 PST - Updated custom rules to detect additional attack permutation 12/5/2025 17:45 PST - Updated custom rules to include additional transform "RemoveNulls".Application layer DDoS protection using the HTTP DDoS Ruleset in Azure WAF
Today, Distributed Denial of Service (DDoS) attacks can strike as soon as public connectivity is enabled, highlighting their widespread prevalence. Factors such as easily accessible botnets, the explosion of IoT devices, and the growth of API-driven workloads, e-commerce platforms, and global web applications have made these attacks easier to launch and more impactful. Importantly, attackers are no longer focusing solely on the network layer, they increasingly target the application layer. Application-layer DDoS attacks often mimic normal user activity, making detection and mitigation far more challenging than traditional network-layer attacks. The most common types of Application layer/HTTP based DDOS attacks are outlined below. Common HTTP-based DDoS attacks: HTTP floods: Large volumes of valid looking GET or POST requests are sent to webpages or APIs, overwhelming application gateways and backend services without saturating network bandwidth. API abuse attacks: Attackers repeatedly call specific API endpoints, such as authentication, search, or checkout that trigger expensive backend operations, quickly exhausting compute and database resources. Slow HTTP attacks: Connections are deliberately kept open by sending data very slowly, consuming server threads and connection limits while generating relatively little traffic. TLS-intensive attacks: A high number of encrypted connections are initiated to increase CPU usage during TLS handshakes, impacting application gateways and load balancers. In order to defend against these sophisticated threats, organizations need application-aware protection that can identify abnormal behavior patterns rather than relying only on traffic volume. This is precisely the capability provided by the HTTP DDoS Ruleset for Azure Application Gateway WAF. What Is the HTTP DDoS Ruleset? The HTTP DDoS Ruleset is a built-in capability of Azure Application Gateway WAF designed to protect your applications from large-scale HTTP floods at the application layer. Unlike static rate-limiting or manual IP blocking, this ruleset uses adaptive learning to understand what “normal” traffic looks like for your gateway and then automatically mitigates anomalies. Key features Baseline learning: The ruleset observes traffic for about 24 hours to establish a normal request pattern per gateway. Dynamic detection: When incoming requests exceed the learned baseline, the ruleset identifies potential abuse (Client-specific or IP specific limits are applied only when the overall request volume to the gateway exceeds its learned baseline). Automated mitigation: Offending clients are blocked and are placed in a “penalty box” for the defined time (15 minutes). Sensitivity levels: Choose low, medium, or high to control aggressiveness. Medium is recommended for most workloads. Leverages Microsoft’s vast global network’s threat intelligence to establish a stricter baseline for suspected botnet traffic and when exceeded, blocks them and places those suspected bots into the penalty box. Threat intelligence plays a critical role here. By continuously aggregating data from global telemetry, threat intelligence systems can identify sources that are likely participating in coordinated attacks. When applied to HTTP DDoS protection, this intelligence allows suspected bot traffic to be treated differently from normal user traffic. Instead of relying only on static blocklists, botnet-aware defenses use reputation, behavior, and historical signals to apply throttling or penalties dynamically. This approach reduces the attack surface, limits the impact of distributed bot-driven floods, and avoids unnecessary disruption to legitimate users. Threat intelligence shifts DDoS defense from a purely reactive posture to a more informed, proactive one, making it far more effective against today’s botnet-driven application-layer attacks. Enabling and validating the HTTP DDoS Ruleset: Getting started with the HTTP DDoS Ruleset on Application Gateway WAF is simple. Enable the Ruleset: In the Azure portal, open your WAF policy. Note: Currently the ruleset is available only in the preview portal: https://preview.portal.azure.com/ Under Managed Rules, Click on Assign and then assign the HTTP DDoS Ruleset_1.0 (Preview) and save. Each rule can be configured to either Log traffic for observation or Deny traffic for active mitigation. Sensitivity can be adjusted to High, Medium, or Low, allowing you to balance detection speed and accuracy. Higher sensitivity enforces lower thresholds and detects anomalies sooner, while lower sensitivity raises thresholds to reduce false positives. Medium sensitivity is the default and recommended setting for most workloads. Once enabled, the ruleset is evaluated early in the WAF pipeline, before custom rules are processed. This ensures that HTTP-based DDoS protection cannot be bypassed by DDoS protection. The ruleset works alongside the Default Rule Set (DRS) and any custom rules for comprehensive security. After the policy is applied to an Application Gateway, the ruleset enters a learning phase that lasts at least 24 hours. During this time, it observes traffic patterns to establish normal baselines for the gateway. No detection or blocking occurs during this period, allowing the ruleset to understand typical application behavior before enforcement begins. Metrics: Once the learning phase completes, traffic surges that exceed the learned baseline are reflected in the Application Gateway metrics. These metrics provide immediate visibility into when the HTTP DDoS ruleset is actively detecting and mitigating abnormal behavior. Metric – WAF Penalty Box Size This metric shows how many IP addresses are currently inside the penalty box, meaning that the WAF has detected them exceeding the learned HTTP DDoS baseline and is temporarily blocking them. A spike here indicates that multiple clients crossed their thresholds at the same time, often during an attack or load-test scenario. Metric – WAF Penalty Box Hits This metric represents how many IPs entered the penalty box. Every time a client breaches its threshold, the ruleset logs a hit and places that IP into the penalty box for approximately 15 minutes. Multiple hits often correlate with repeated spikes or sustained abusive traffic patterns. Logs: For deeper analysis, enabling diagnostic settings allows you to inspect HTTP DDoS Ruleset events directly in the logs. These logs provide granular details about which IPs were flagged, why they were flagged, and how far they exceeded expected thresholds. Example of DetailedData from a log: RemoteAddress: 4.x.x.x (Public IP) crossed threshold. Expected: 4400.000000 request per 900 seconds, Actual: 8407.000000 requests per 900 seconds. KQL queries to retrieve these logs: Resource specific logs: AGWFirewallLogs | where RuleSetType == "Microsoft_HTTPDDoSRuleSet" Diagnostic logs: AzureDiagnostics | where Category == "ApplicationGatewayFirewallLog" | where ruleSetType_s == "Microsoft_HTTPDDoSRuleSet" Note: Identify IPs repeatedly flagged and confirm they’re malicious, not legitimate clients. Conclusion: The threat landscape continues to evolve, and defenses must evolve with it. Leveraging the HTTP DDoS Ruleset in Azure Application Gateway WAF helps ensure protections keep pace with modern application-layer attacks. With built-in visibility through metrics and logs, teams can better understand traffic behavior and operate their WAF with greater confidence. Next Steps: Access the HTTP DDoS ruleset for Application Gateway via the preview portal: https://preview.portal.azure.com/ HTTP DDoS Ruleset (Preview) - Application Gateway WAF | Microsoft Learn Azure Web Application Firewall (WAF) policy overview | Microsoft LearnGeneral Availability of JavaScript Challenge in Azure Front Door WAF
We are pleased to announce the General Availability (GA) of the JavaScript Challenge feature for Azure Web Application Firewall (WAF) on Azure Front Door. This capability equips organizations with a seamless, invisible anti-bot verification layer that distinguishes legitimate users from malicious scripts helping protect web applications from automated threats while preserving a smooth user experience. Azure WAF JavaScript Challenge Modern bot attacks are increasingly evasive, often bypassing traditional defenses like IP based blocking or simple rate limits. The JavaScript Challenge introduces a lightweight, browser-based verification step that helps distinguish legitimate users from automated scripts without requiring user interaction. Benefits of the JavaScript Challenge include: Low friction for legitimate users: Genuine users experience minimal latency or interruption since no manual interaction is required. Stronger bot protection: Automated tools and scripts fail to pass the computational challenge, enabling more effective blocking of bad bots. Flexible enforcement: You can target specific endpoints (e.g., login, registration, checkout flows), apply to bot manager or custom rules, and adjust cookie lifetimes to align with your user experience goals. How JavaScript Challenge Works The JavaScript Challenge is configured as an action in either custom rules or in the Bot Manager ruleset. When a client’s HTTP/S request matches a rule with this action, Azure WAF directs the browser to a lightweight challenge page. The page runs a short computational task automatically usually invisible to the user. If the browser successfully completes the computation, the request is validated and allowed to proceed, confirming that it originated from a legitimate user. If the challenge fails, the request will be blocked, preventing automated bots from accessing the application. Getting Started If you have been using JavaScript Challenge during the public preview, your existing configurations will continue to work. For new users, simply enable the JavaScript Challenge action in your WAF policy and define the triggering conditions. For more details on configuration and best practices, check out our earlier blogs: Azure WAF Public Preview: JavaScript Challenge | Microsoft Community Hub Azure WAF’s Bot Manager 1.1 and JavaScript Challenge: Navigating the Bot Threat Terrain | Microsoft Community Hub Documentation Web Application Firewall JavaScript Challenge | Microsoft Learn
