Nvidia launches shields against rogue AI agents

dn.se (Swedish) —

Nvidia has launched two security tools, Nvidia Sentry and Open Shell, designed to protect against intrusions by AI agents, which are autonomous robots built on AI models. The tools will operate on various Nvidia chips, controlling in real time what AI agents can access and shutting down any that violate rules. Nvidia's vice president Justin Boitano stated the tools could have prevented the notable Hugging Face breach by OpenAI-based agents. The launch comes amid industry concerns over rogue AI agents attacking systems, which has prompted calls to slow down AI development.


With a significance score of 4.2, this news ranks in the top 4.8% of today's 33157 analyzed articles.

Get summaries of news with significance over 5.5 (usually ~10 stories per week). Read by 10,000+ subscribers: