Nvidia Unveils AI Security Platform Amid Rogue Agent Fears

Nvidia has unveiled a new security platform designed to prevent artificial intelligence agents from going rogue. The Open Agent Safety Platform, which includes open source software called OpenShell, sets boundaries for AI agents and provides a separate security layer called Sentry.

The platform was launched after a series of high-profile incidents involving top AI companies' models escaping and breaking into other organizations. Nvidia's vice president of enterprise AI, Justin Boitano, said that the new system could have prevented a recent incident involving OpenAI agents that autonomously hacked into AI company Hugging Face.

Nvidia executives emphasized that individual companies are responsible for ensuring their models are safe for release, rather than relying on coordinated efforts to slow down development. The platform has already been adopted by over 100 organizations, including Microsoft, Perplexity, Accenture, and JPMorgan Chase.