AI applications introduce new security risks, from prompt injection and malicious content to abuse, excessive resource consumption, and changes to the underlying cloud environment. In this session, we’ll explore how to start protecting AI applications built with Azure OpenAI in Microsoft Foundry by using Azure-native telemetry and Microsoft Sentinel. Through practical demos, we’ll bring together Foundry Prompt Shields, application telemetry, Azure OpenAI diagnostics, and Azure Activity data to detect prompt attacks, identify repeated malicious behavior, monitor unusual AI usage, create Sentinel analytics rules, and investigate activity across the application and Azure control plane. We’ll also briefly discuss how this approach can be extended with the broader Microsoft Security stack, including services such as Microsoft Defender for Cloud, Defender XDR, and Microsoft Purview, for organizations that want more integrated posture management, threat protection, investigation, and governance. The goal is to provide a practical entry point into AI application security and understand what can already be done with Microsoft Sentinel and Azure-native telemetry, then see how the wider Microsoft Security ecosystem can build on that foundation.

Organizations generate vast amount of security data every day, yet many struggle to extract real value from their SIEM investments. With real-world projects and operational experience, this session explores intelligent log collection, use case-driven monitoring and data optimization. Attendees will gain practical guidance on transforming raw logs into actionable intelligence while improving detection capabilities, operational efficiency, and return on investment.

AI applications introduce new security risks, from prompt injection and malicious content to abuse, excessive resource consumption, and changes to the underlying cloud environment. In this session, we’ll explore how to start protecting AI applications built with Azure OpenAI in Microsoft Foundry by using Azure-native telemetry and Microsoft Sentinel.

Through practical demos, we’ll bring together Foundry Prompt Shields, application telemetry, Azure OpenAI diagnostics, and Azure Activity data to detect prompt attacks, identify repeated malicious behavior, monitor unusual AI usage, create Sentinel analytics rules, and investigate activity across the application and Azure control plane.

We’ll also briefly discuss how this approach can be extended with the broader Microsoft Security stack, including services such as Microsoft Defender for Cloud, Defender XDR, and Microsoft Purview, for organizations that want more integrated posture management, threat protection, investigation, and governance.

The goal is to provide a practical entry point into AI application security and understand what can already be done with Microsoft Sentinel and Azure-native telemetry, then see how the wider Microsoft Security ecosystem can build on that foundation.

Organizations generate vast amount of security data every day, yet many struggle to extract real value from their SIEM investments. With real-world projects and operational experience, this session explores intelligent log collection, use case-driven monitoring and data optimization. Attendees will gain practical guidance on transforming raw logs into actionable intelligence while improving detection capabilities, operational efficiency, and return on investment.

Ova tehnička radionica vodi sudionike kroz ključne komponente Microsoft Sentinel platforme, uključujući arhitekturu, metode prikupljanja logova i integraciju s različitim izvorima logova (Syslog, Windows, cloud servisi). Demonstrirat ćemo kako dizajnirati skalabilan i troškovno optimiziran model prikupljanja podataka, uključujući filtering na log forwarderima i korištenje Data Collection Rules (DCR). Sudionici će dobiti konkretne primjere iz prakse kako balansirati između sigurnosne vidljivosti i troškova te kako uz potencijalno korištenje AI-a povećati učinkovitost i smanjiti vrijeme reakcije.