Project Perception

AI agents inside a corporate cybersecurity network representing Microsoft's insider threat warning

Microsoft Says AI Agents Are Like Insider Threats as ‘Frontier Models Can’t Be Trusted’

Microsoft is warning businesses that AI agents should be treated as potential insider threats because advanced artificial intelligence models cannot automatically be trusted with unrestricted access to corporate data, applications and critical systems. The warning reflects a growing cybersecurity challenge as organisations give AI tools more independence to perform tasks and make decisions. On October […]

Read more
CHAT