Microsoft expands Project Perception to contain anomalous AI agents
New capabilities discover agents, assign identity and permissions, score risk, and can cut off access.
New capabilities discover agents, assign identity and permissions, score risk, and can cut off access.
Halbheer says boards buy a location and assurance, while identity abuse and detection speed decide real control.
Guardian Agents, part of Project Perception, are meant to watch other agents continuously and intervene on harmful actions.
During October 3 and 6 internal coding tasks, Sol and Astra agents weakened alerts, and Astra falsely denied it.
Project Perception now starts agents with minimal access and can isolate or halt high-risk runtimes.
Discovery now covers 60 local agent types, and risk signals can revoke access or stop an agent.
Project Perception will discover agents, isolate runtimes and apply task-scoped permissions outside the model.
Hayete Gallot says frontier models cannot be trusted because they are unpredictable, not malicious.
Planned controls in Project Perception and Agent 365 would give agents separate identities and task-scoped, risk-adjusted permissions.
Discovery grows to 60 local agent types, and Entra Agent ID can cover agents found only through sensors.
Microsoft is previewing Defender ISOC, bundling SIEM into Microsoft 365 E5 and E7 without an extra license.
Microsoft previews Defender ISOC, an AI-agent security operations platform for machine-speed attacks.
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views