Improve Campaign Reach and Measurement with Azure Confidential Clean Rooms
Why campaign performance now depends on trusted data collaboration For many years, third-party cookies helped advertisers, publishers, and measurement partners recognize users across parts of the open web. That model continues to evolve as browsers and mobile platforms introduce stronger privacy protections and limit access to certain cross-site and device-level identifiers. As a result, some advertisers and publishers are placing greater emphasis on the first-party data they collect directly to support audience activation and campaign measurement. Advertising partnerships may involve identifiers and behavioral data covered by privacy, data-protection, or industry rules. Data that has been altered to reduce direct identification—such as hashed email addresses or advertising identifiers—may still be linked to individuals and should not automatically be considered anonymous. Depending on the law and context, it may be treated as personally identifiable information (PII) or personal data under the European Union’s General Data Protection Regulation (GDPR). Organizations must have an appropriate legal basis and a clear purpose for using such data. The European Union’s Digital Markets Act (DMA) also affects how designated digital platforms combine certain personal data across services. In the United States, health information held by organizations covered by the Health Insurance Portability and Accountability Act (HIPAA) may be subject to additional restrictions, including for some marketing uses. The requirements for each collaboration depend on the parties, data, purpose, consent or authorization, and jurisdiction. Together, these changes create a practical challenge: campaign analysis increasingly depends on combining detailed records held by different organizations, but privacy, security, and governance obligations make unrestricted exchange of customer-level data difficult. Advertisers and publishers therefore need a controlled way to match audiences and measure outcomes using only authorized data—without exposing or freely sharing the underlying records. Azure Confidential Clean Rooms is designed to address this challenge. It allows each party’s detailed data to be used for an agreed analysis while helping protect raw data from access by other participants. This provides a controlled, verifiable environment for audience matching and campaign measurement without unrestricted file sharing. What campaign leaders should look for: the potential to broaden addressable audiences, strengthen evidence of campaign lift, reduce operational risk, and establish a repeatable model for trusted collaboration across media and measurement partners. Campaign decisions with secure multiparty analytics Azure Confidential Clean Rooms is a fully managed service that enables advertisers, publishers, agencies, and measurement partners to analyze sensitive datasets together while helping protect each participant’s raw data. The current preview supports analytics through Spark SQL queries agreed by the participants. These queries run in a hardware-protected environment called a Trusted Execution Environment (TEE), helping protect participants’ raw data from other collaborators and the Azure operator throughout its lifecycle. For a deeper explanation of the technology and architecture, see our earlier blog, Preview of multiparty analytics with Azure Confidential Clean Rooms. The following scenarios show how this model supports specific campaign decisions: Audience activation — Which high-value customers might this media partner reach? The advertiser contributes first-party customer data, such as securely transformed contact details, postal addresses, loyalty IDs, and purchase history. The publisher contributes its audience-matching data, on-site behavior, and consented interest or demographic segments. Azure Confidential Clean Rooms can compare identifiers that the participants have agreed to use for matching and release a reachable audience segment without exposing the underlying records. Campaign leaders can use the result to estimate potential reach and direct investment toward more relevant audiences. Identity enrichment — Can we improve match quality while protecting partner data? An agency or identity partner can contribute a third dataset to connect approved identifiers across email, mobile advertising IDs, devices, or households and add consented demographic or business attributes. Because the matching happens inside the confidential clean room, participants may improve match rates without exposing the identity partner’s underlying data or copying another party’s identifiers. Stronger matching can help expand reach and reduce media waste caused by fragmented customer identities. Measurement and attribution — Did the campaign contribute to additional business outcomes? The publisher contributes ad-exposure records, while the advertiser contributes outcomes such as purchases, order values, subscriptions, or app installs. Comparing these approved datasets can help measure unique reach and frequency, results across publishers, and the difference between groups that were and were not exposed to the campaign. For example, a retailer and a streaming publisher can compare exposure data with purchase outcomes to estimate campaign lift without revealing who saw a specific ad or made a purchase. This can give campaign leaders stronger evidence for campaign optimization and future budget allocation. These scenarios can help campaign leaders assess whether secure data collaboration may improve audience reach, matching quality, or confidence in campaign measurement. Why campaign leaders should consider Azure Confidential Clean Rooms The collaboration model is designed to give each participant greater control over how its data is accessed, used, and shared. Four capabilities are central to building trust among advertisers, publishers, agencies, and measurement partners: No centralized data pooling — Collaborators can keep source datasets in their own storage instead of copying them into a shared, permanent repository. The confidential environment verifies that expected code is running before it securely retrieves authorized data for temporary processing. This can reduce unnecessary data movement and exposure while supporting an approved analysis across partners. Controlled release of approved results — Before analysis begins, collaborators can agree which data may be used, approve the analysis, and specify who may receive the results. Safeguards can also prevent results for very small groups from being released, helping reduce the risk of identifying an individual. Verifiable governance and tamper-resistant audit trails — Participants can verify key properties of the environment instead of relying only on the clean-room provider’s claims. Open-source components and hardware-backed verification help participants confirm that the expected Microsoft-provided code is running. Tamper-resistant audit trails generated in the confidential environment can support compliance reviews. Data protection throughout the process — Each party can encrypt its data before it leaves its environment. Participants allow access to encryption keys only after the confidential environment verifies that expected code is running. Try Azure Confidential Clean Rooms Consider a campaign where better partner data could help improve audience reach, matching quality, or measurement confidence. Sign up to participate in a preview of multiparty analytics with Azure Confidential Clean Rooms. The Microsoft team will contact you to discuss the campaign scenario, participating datasets, and governance requirements. Learn more Sign-up: Preview of multiparty analytics with Azure Confidential Clean Rooms Preview blog: Multiparty analytics with Azure Confidential Clean Rooms Azure documentation: Confidential Clean RoomsMicrosoft Defender for Cloud Customer Newsletter
*This will be the last monthly MDC newsletter. To keep up with the latest, please visit: What's new in MDC What's new in Defender for Cloud? Multiple container security features are now Generally Available: Container-level misconfiguration recommendations for Kubernetes, Upgrade AKS version recommendations, VA for runtime-discovered container images on EKS and GKE, Kubernetes notes VA for EKS and GKE, scanning support for Docker hardened container images. For more information, see this page here. Database-level recommendations for SQL VA now GA The SQL vulnerability assessment recommendations created as part of the transition from grouped to individual recommendations are now generally available. Each SQL vulnerability assessment rule is surfaced as its own recommendation, reported directly on the affected SQL database resource. For more details, please refer to this documentation . Blogs of the month In July, our team published the following blog posts we would like to share: 1. Built to Protect: The Architecture Behind Codename MDASH Customer journey Discover how other organizations successfully use Microsoft Defender for Cloud to protect their cloud workloads. This month we are featuring NTT Data. NTT Data, a top global IT services provider, leverages Azure, OpenAI and Microsoft Defender to launch their AI agents, adopting secure by design principles, to help enhance, competitiveness organization change and data usage. Defender for AI, and Defender CSPM, as part of the Defender family, address the emerging risks and threats like prompt injection and data poisoning that come with generative AI. Join our community! We offer several customer connection programs within our private communities. By signing up, you can help us shape our products through activities such as reviewing product roadmaps, participating in co-design, previewing features, and staying up-to-date with announcements. Sign up at aka.ms/JoinCCP. We greatly value your input on the types of content that enhance your understanding of our security products. Your insights are crucial in guiding the development of our future public content. We aim to deliver material that not only educates but also resonates with your daily security challenges. Whether it’s through in-depth live webinars, real-world case studies, comprehensive best practice guides through blogs, or the latest product updates, we want to ensure our content meets your needs. Please submit your feedback on which of these formats do you find most beneficial and are there any specific topics you’re interested in https://aka.ms/PublicContentFeedback. Note: If you want to stay current with Defender for Cloud and receive updates in your inbox, please consider subscribing to our monthly newsletter: https://aka.ms/MDCNewsSubscribe
Unable to install SQL Server 2022 Express (installer glitch + SSMS error)
Hi, I recently purchased a new Lenovo laptop, and I am trying to install Microsoft SQL Server 2022 Express along with SSMS. SSMS installed successfully, but SQL Server installation fails, and sometimes the installer UI glitches or does not load properly. Because of this, I am getting connection errors in SSMS like "server not found" and "error 40". I am not very familiar with technical troubleshooting. Can someone guide me step-by-step in a simple way to install SQL Server correctly? Thank you.
Feature Proposal: Ability to Exclude a column/subset of Columns in Select.
Summary I would like to propose a new T-SQL feature that allows developers to select all columns from a table while explicitly excluding a small subset of columns. Currently, when a table contains many columns and only one or two need to be omitted, developers are forced to mention every remaining column manually in the "Select" SQL. This leads to verbose queries, reduced maintainability, and a higher chance of mistakes when the schema evolves. Motivation Consider a table with 20 or more columns. Current approach, SELECT EmployeeId, FirstName, LastName, Department, Designation, Email, PhoneNumber, DateOfBirth, Address, City, State, Country, PostalCode, ManagerId, JoiningDate, LastModifiedDate, Status, IsActive, CreatedDate FROM Employees; If the intention is simply to exclude a single sensitive column such as Salary, the query becomes unnecessarily long. A more concise alternative could be: SELECT * FROM Employees EXCLUDE (Salary); The engine would expand * internally and remove the specified columns before execution. Benefits 1. Reduces boilerplate code. 2. Improves readability for wide tables. 3. Makes queries easier to maintain as schemas evolve. 4. Reduces the likelihood of accidentally omitting newly added columns. 5. Makes it simpler to exclude sensitive or internal-use columns from result sets. Expected Behavior Single column exclusion SELECT * FROM Employees EXCLUDE (Salary); Returns all columns except Salary. Multiple column exclusion SELECT * FROM Employees EXCLUDE (Salary, PasswordHash); Returns all columns except Salary and PasswordHash. Suggested Validation Rules 1. Every excluded column must exist in the projected result set. If an excluded column does not exist, compilation should fail with an appropriate error. 2. Duplicate column names in the exclusion list should either: be ignored, or produce a validation error. 3. If the exclusion list removes every projected column, the statement should fail. Example: SELECT * FROM Employees EXCLUDE (Employee, Name, Salary); If these are the only columns in the table, an error could be raised such as: The EXCLUDE clause cannot eliminate all columns from the SELECT list. Returning a zero-column result set would likely be confusing and less useful. Additional Considerations This syntax could also be valuable when selecting from joins, views, or derived tables, where developers frequently want "everything except a few fields." Closing Thoughts I believe this would be a practical quality-of-life enhancement for T-SQL that addresses a common developer pain point while remaining simple to understand and implement. It would reduce repetitive code and improve maintainability without affecting existing queries.
Windows server 2025 SQL patching cluster problem.
Dear Team, I have a problem when I am patching upgrade windows server 2025 with KB5091157. After patching is the clustering is not able to join back; it shows the error with credentials. The log error is "Cannot connect sqlxxxxxxx." you do not have administrative privileges on the cluster. Contact your network administrator to request access. Note: The server is not in a different VLAN network.New Microsoft Certified: SQL AI Developer Associate Certification
AI is transforming how data-driven applications are built, and SQL professionals are at the center of this new era. Whether you're a database developer, administrator, analyst, or architect, your SQL expertise is more critical than ever. With the rise of AI, quality data and secure, optimized queries are foundational to building intelligent, scalable solutions. We’re introducing the Microsoft Certified: SQL AI Developer Associate Certification to help you validate your ability to integrate AI capabilities directly into SQL-based solutions without needing to move your data, learn entirely new platforms, or move away from the T-SQL skills you already use every day. To earn this new Certification, you need to pass Exam DP‑800: Developing AI‑Enabled Database Solutions, currently in beta. Is this the right Certification for you? The Microsoft Certified: SQL AI Developer Associate Certification is designed for SQL professionals who build and maintain SQL-based applications and who want to integrate AI capabilities directly into their data solutions. As you collaborate closely with application developers, database administrators, architects, AI engineers, and DevSecOps teams, skills validated by this certification support the delivery of scalable, secure, and high-performance AI‑enabled applications. This Certification demonstrates your ability to: Design and build database solutions using structured and semi-structured data. Use AI-assisted tools to accelerate SQL development and database management. Secure, optimize, and deploy enterprise-grade SQL solutions. Implement vectors, embeddings, and retrieval-augmented generation (RAG) patterns within SQL database architectures. As a candidate for this Certification, you should have experience writing T-SQL, developing databases on Microsoft SQL platforms, and working with continuous integration and continuous deployment (CI/CD) workflows in GitHub. We also recommend familiarity with AI concepts, such as embeddings, vectors, and models, in addition to AI-assisted development tools. Skills measured by the exam include: Applying advanced T-SQL techniques for AI-ready database solutions. Building vector and semantic search experiences directly in SQL. Implementing RAG workflows to ground large language model (LLM) outputs and reduce hallucinations. Integrating LLMs into SQL-based applications without migrating data. Designing secure, compliant, and scalable AI-enabled data solutions. Exposing SQL data through APIs by using Data API builder. Building and monitoring data APIs by using Data API builder and event-driven change patterns. These capabilities power use cases like semantic and hybrid search, chatbots, personalized recommendations, fraud detection, and predictive analytics. Ready to prove your skills? The first 300 candidates can save 80% Take advantage of the discounted beta exam offer. The first 300 people who take Exam DP-800 (beta) on or before April 3, 2026, can get 80% off. To receive the discount, when you register for the exam and are prompted for payment, use code DP800Belzoni. This is not a private access code. The seats are offered on a first-come, first-served basis. As noted, you must take the exam on or before April 3, 2026. Please note that this discount is not available in Turkey, Pakistan, India, or China. How to prepare Get ready to take Exam DP-800 (beta): Review the Exam DP-800 (beta) exam page for details. The Exam DP-800 study guide explores key topics covered in the exam. Work through the self-paced skilling Plan on Microsoft Learn: Become a SQL AI Developer: Prepare for Certification Exam DP-800. Connect with Microsoft Training Services Partners in your area for in-person offerings. Need other preparation ideas? Check out Just How Does One Prepare for Beta Exams? Ready to get started? Remember, the number of spots is limited to the first 300 candidates taking Exam DP-800 (beta) on or before April 3, 2026. Beta exam rescoring begins when the exam goes live, with final results released approximately 10 days later. For more details, read Creating high-quality exams: The path from beta to live. Stay tuned for general availability of this Certification in May 2026. Additional information You can take Certification exams online, from your home or office. Learn what to expect in Online proctored exams: What to expect and how to prepare. For more cloud and AI Certification updates, read our recent blog post, The AI job boom is here. Are you ready to showcase your skills? Get involved: Help shape future Microsoft Credentials. Join our Microsoft Worldwide Learning SME Group for Credentials on LinkedIn for beta exam alerts and opportunities to help shape future Microsoft learning and assessments. Explore Microsoft Credentials on AI Skills Navigator.Preview of multiparty analytics with Azure Confidential Clean Rooms
Today, we are excited to announce the preview of multiparty analytics feature of Azure Confidential Clean Rooms, a fully managed service that allows customers and their partners to securely analyze privacy-sensitive datasets from multiple parties. It uses confidential compute enabled Apache Spark-based big-data analytics (Spark SQL) which helps protect their raw data from other collaborators and from the Azure operator by performing computations in a Trusted Execution Environment (TEE). Privacy-sensitive datasets include personally identifiable information (PII), protected health information (PHI) and cryptographic secrets. Organizations across industries are increasingly looking to supplement their data with data from business partners, to build a complete view of their business. For example, brands, publishers, and their partners need to collaborate using datasets containing Intellectual Property (IP) to improve the relevance of their campaigns. Confidential data clean rooms help solve this challenge by enabling organizations to share and analyze granular datasets in a secure environment that helps prevent raw data exfiltration—protecting intellectual property, preserving customer privacy, and addressing concerns around regulatory compliance. You can sign up for the preview here Key Features Fully Managed: Azure takes care of the infrastructure provisioning and scaling with no user intervention. This significantly reduces your onboarding effort allowing you to focus on the queries and insights, not on infra management. Confidential Spark SQL: Spark SQL allows you to query large datasets and run complex queries in a distributed computing environment. In the confidential computing enabled version, the Spark driver and executors are fully attested policy-governed enclaves running as virtual nodes on confidential Azure Container Instances (ACI) which helps prevent exfiltration of collaborators’ data during query execution. Governance: Helps manage membership to cleanrooms, enables and verifies approval for queries from relevant collaborators before executing them and verifies consent to access sensitive collaborator data. It also helps generate tamper-resistant audit trails containing salient clean room events. This is made possible with the help of an implementation of the Confidential Consortium Framework (CCF). Telemetry: Throughout every clean-room run, detailed logs are streamed out in real time to monitor performance, troubleshoot issues, and keep the analytics healthy — all without ever exposing the collaborators’ data at any time. Verifiable trust: Cryptographic remote attestation viz. full attestation based on confidential hardware reports allows independent verification of the TEE along with along with all components that are part of it, without just trusting the cloud provider, before sensitive data and decryption keys are made available to the TEE Open-source containers: All Microsoft provided cleanroom containers and sidecars are open-sourced here and can be verified for provenance and integrity guarantees using GitHub artifact attestation Use Cases Multi-party confidential big-data analytics unlocks value in scenarios where data sensitivity, regulatory pressure, or competitive concerns previously blocked collaboration. These are some early scenarios that can benefit from this. Media & Advertising Collaboration of advertiser CRM data with publisher data for audience targeting and segment activation. Collaboration of audience data with measurement partners for measurement and attribution. Banking & Finance Collaboration between banks and insurance firms to upsell relevant products to existing bank customers without sharing raw data from either side Collaboration with retailers to generate customized offers for bank customers, without exposing either party’s underlying data. Government & Public Sector Secure collaboration of data across government departments to deliver better citizen welfare outcomes. Secure collaboration between government and private enterprises on shared-interest workloads such as traffic monitoring and weather systems. Healthcare Enable healthcare firms — including biopharma organizations — to combine their data with third-party institutions to accelerate clinical development, like identifying eligible participants for a clinical trial, without exposing underlying patient data. Combine patient datasets across hospitals to study disease patterns or outcomes without exposing sensitive protected health information. "A higher standard for protecting user privacy and trust, the phase-out of third-party cookies, and global regulations demand more sophisticated data collaboration tools to support advertising marketplaces. Azure Confidential Cleanrooms (ACCR) provides a secure, feature-rich, and flexible foundation to implement privacy-preserving functions and enable insights without sharing privacy-sensitive data outside of organization boundaries. Built on the Azure Confidential Compute (ACC) platform and offering cohesion with Azure's diverse set of services, ACCR offers the attestation, audit, fine-grained access control, and verifiable trust tools required for secure and privacy-safe data collaboration in today's world." — Andrei Mackenzie, Engineering Manager, Microsoft AI "Azure Confidential Clean Rooms enabled our team to evaluate how clean room capabilities can support secure, governed data collaboration at scale. Through the Proof-of-Concept (PoC), we explored how privacy-preserving workflows, trusted access controls, and scalable compute can create a stronger foundation for responsibly leveraging first-party data. This helps reduce operational friction while supporting business growth, improving customer engagement, and enabling more relevant customer experiences." — Nic Dregne, Director, Microsoft AdTech Engineering Beyond Spark SQL Realizing other multi-party scenarios like custom analytics, ML training and inferencing on Azure Confidential Clean Rooms is in our roadmap. If you have such a scenario to be realized, you can fill in and submit the preview signup form with the details of your scenario and we’ll get back to you. Learn More · Signup for the preview of Azure Confidential Clean Rooms for Analytics · Confidential Consortium Framework (CCF) · Virtual Nodes on Azure Container InstancesLogic Apps, Windows auth, the On-Premises Data Gateway and you
I was working with a customer recently who had a somewhat unusual situation, unusual in that I have become accustomed to most government customers having an Express Route or site-to-site VPN connection to connect their on-premises network to their Azure environment. However, this customer had a need to connect to an on-premises SQL instance via the on-premises data gateway (OPDG). The OPDG is installed as a Windows service on a machine inside the on-premises network and, when registered in Azure, allows Azure resources to connect to services on premises (more here). I did not have any direct experience with this tool but worked with the customer to get it installed on their network, which included getting it to work with their proxy (thanks to the larger Microsoft team for the assist and thanks to the customer for their patience figuring this out). We got the gateway registered in Azure and were ready to test it out. The customer is using Logic Apps and the SQL Connector to connect back to their on-premises SQL instance. The initial attempt to connect to SQL using SQL credentials was successful (Yay!!!) but the customer wanted to use Windows Authentication (which is a best practice). However, when trying to establish the connection with Windows Authentication, they were getting the error "status 401 - Credentials are missing or not valid...The credentials provided for the SQL source are invalid." Doing a little sleuthing in the Security logs on the SQL server, we could see that the authentication attempt being made, but with null credentials. Of course! We're passing our Windows credentials to the OPDG, but we haven't configured the gateway service account with delegation permissions to pass them on to SQL! To configure the on-premises data gateway account for delegation, do the following: Create a Service Principal Name (SPN) using the setspn command line tool for the OPDG service account: setspn -S gateway\gatewayMachineName domainname\gatewaySvcAcctName Open Active Directory Users and Computers (ADUC) and locate the OPDG service account Open the Delegation tab and select "Trust this user for delegation to specified services only" and "Use Kerberos Only" then add the services for which you want the OPDG to have delegation, e.g. SQL Server. Once this was done, we could create the Logic Apps SQL Connection successfully. A good check is to see if you can enumerate the list of tables in the database to which you are querying. As it turns out, there is fairly good documentation on this topic under the Power BI documentation, but searching for this under the context of Logic Apps didn't yield much success! In any case, I hope this helps someone else in the future!
