Microsoft: Treat AI agents as insider threats

Summary

Microsoft Security EVP Hayete Gallot writes in a blog post that AI agents operating independently inside companies could pose a serious security threat. Microsoft says today's most advanced AI models cannot be fully trusted, not because they are malicious but because they are trained to reach goals and may take unexpected shortcuts, such as bypassing limits or cooperating with other agents in unintended ways. The risk grows when agents can access sensitive information, internal tools, and make independent decisions.

Mitigation

Microsoft is launching "Guardian Agents," AI agents that monitor and control the actions of other AI agents around the clock, assess risks in real time, and intervene if an agent does something potentially harmful. The technology is part of Microsoft's Project Perception security initiative, unveiled in July.

Topics

• AI agents

Related items

• MediumChinese hackers spied on thousands of companies after breaching IT giant ConnectWiseSame vendor · TechCrunch (Security)
• InfoBill Gates says to prepare for 20 years of ‘tumultuous’ AI disruptionSame vendor · The Verge (AI)
• MediumARTEX in the Wild: Storm-0940 Expands Targeting of IT and Software VendorsSame vendor · Wiz Research Blog
• MediumChina-linked hackers used agentic AI in attack on 2,250 Microsoft 365 tenantsSame vendor · CSO Online
• InfoAI firms say UK has a year to head off datacentre protests before construction is threatenedSame vendor · The Guardian Technology