Microsoft expands Project Perception to contain anomalous AI agents
New capabilities discover agents, assign identity and permissions, score risk, and can cut off access.
1
Stories per day · 30 days
Relatedai-agents5microsoft5entra3insider-threat2agent-identity1conditional-access1guardian-agents1microsoft-defender1prompt-injection1
7 stories, newest first · one card per story
Stories tagged #project-perception
Microsoft says AI agents should be treated as insider threats
Guardian Agents, part of Project Perception, are meant to watch other agents continuously and intervene on harmful actions.
Microsoft adds dynamic permissions and risk scores for AI agents
Project Perception now starts agents with minimal access and can isolate or halt high-risk runtimes.
1
Microsoft warns prompt injection can hijack enterprise AI agents
Project Perception will discover agents, isolate runtimes and apply task-scoped permissions outside the model.
4
Microsoft extends Project Perception to secure AI agents as insiders
Discovery grows to 60 local agent types, and Entra Agent ID can cover agents found only through sensors.
Microsoft Rebuilds the SOC with AI Agents, SIEM Integration and Machine-Speed Defense
Microsoft previewed an integrated SOC pairing Defender, SIEM, and AI agents for faster response.
Microsoft Rebuilds the SOC With AI Agents to Fight Machine-Speed Cyberattacks
Microsoft previews Defender ISOC, an AI-agent security operations platform for machine-speed attacks.