Anthropic · Microsoft · AI Agent · OpenAI · Nvidia · Mythos · TechCrunch AI
Microsoft confirms AI agents are like insider threats as ‘frontier models can’t be trusted’
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
Microsoft on Monday introduced new security features designed to protect enterprises from the growing threat of AI agents.
Key facts
- In addition to Guardian Agents, it has added an agent detection feature to its Microsoft Defender product that can find up to 60 types of agents that employees bring into the workplace, including
- Microsoft was an inaugural member of Nvidia’s new Open Agent Safety Platform, which garnered the support of more than 100 other tech companies
- When announcing Guardian Agents, Microsoft’s security business chief Hayete Gallot was even more straightforward
- Perhaps the most notable addition is Guardian Agents, a new feature intended to monitor the AI agents a company uses
Summary
Perhaps the most notable addition is Guardian Agents, a new feature intended to monitor the AI agents a company uses. Project Perception was Microsoft’s answer to powerful hacking models like Anthropic’s Mythos and Fable and OpenAI’s security vulnerability scanning system Daybreak. The product was designed around the assumption that AI hackers would come from outside the company. Earlier this month, in his private blog, Nadella warned that it’s time to stop trusting AI model providers, even if they offer assurances of safety and security with their agentic products.