Microsoft Defender for AI Services

Detects and alerts on threats targeting generative AI workloads at runtime — including prompt injection, jailbreak attempts, data leakage, and credential theft — for applications built on Azure OpenAI and Azure AI Foundry.

Capabilities

  • AI threat protection
    Secure Infrastructure

    Detects attacks and anomalous usage patterns targeting Azure OpenAI and Azure AI Services — including credential abuse, data exfiltration attempts, data poisoning, and suspicious prompt patterns — surfacing alerts in Defender for Cloud.