logo
About Contact

Microsoft Raises Alarm on Trust Issues with AI Agents, Citing Insider Threat Risks

Technology News

Microsoft Raises Alarm on Trust Issues with AI Agents, Citing Insider Threat Risks

Microsoft says AI agents are like insider threats as ‘frontier models can’t be trusted’

TechCrunch

Microsoft says AI agents are like insider threats as ‘frontier models can’t be trusted’

Microsoft wants enterprises to closely watch the agents that employees use with systems not controlled by AI labs like OpenAI and Anthropic.

'AI models cannot be trusted': Microsoft warns of insider threats, expands Project Perception

Business Today

'AI models cannot be trusted': Microsoft warns of insider threats, expands Project Perception

Models have been trained to attain results, which often leads to reward hacking, and models are not optimized around organizational norms or judgment, says Hayete Gallot, Executive Vice President...

Microsoft: "Frontier AI models, regardless of their origin, cannot be trusted"

Neowin

Microsoft: "Frontier AI models, regardless of their origin, cannot be trusted"

Microsoft says frontier AI models cannot be trusted and urges companies to treat powerful AI agents as potential insider threats.

AI agents can pose insider security risks even without being hacked: Microsoft

Mint

AI agents can pose insider security risks even without being hacked: Microsoft

Artificial intelligence (AI) agents deployed within companies could pose significant internal security risks even without being compromised by hackers, Microsoft has warned, calling for continuous...

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.