logo
About Contact

Microsoft Expands Project Perception to Tackle Risks of Rogue AI Agents

Technology News

Microsoft Expands Project Perception to Tackle Risks of Rogue AI Agents

‘Frontier models cannot be trusted’: Microsoft expands Project Perception to continuously assess AI agent risk

Firstpost

‘Frontier models cannot be trusted’: Microsoft expands Project Perception to continuously assess AI agent risk

Microsoft is expanding Project Perception to monitor AI agents continuously, adjust their permissions based on risk and contain potentially harmful actions through security controls outside the...

NewsBytes

Microsoft announces Project Perception expansion to restrict risky AI actions

Microsoft enhances Project Perception to continuously monitor AI agents, adjusting permissions based on risk and containing threats with external security controls.

Microsoft unveils tools to monitor and corral rogue AI agents

GeekWire

Microsoft unveils tools to monitor and corral rogue AI agents

New features in Microsoft 365 E7 and Project Perception will assess each agent's risk, with the ability to block it from making changes, require human intervention or shut it down. Read More

Microsoft targets the 'agentic insider' with new controls for rogue AI agents

SiliconANGLE

Microsoft targets the 'agentic insider' with new controls for rogue AI agents

Microsoft Corp. today introduced security controls for rogue artificial intelligence agents that cut back what an agent may do as its assessed risk climbs.The release takes on what Hayete Gallot,...

Coverage dates

First reported:

First saved on ClustZ:

Coverage updated:

We use cookies to improve your experience and analyze site traffic. By clicking "Accept", you agree to our use of cookies. See our Privacy Policy.