OpenAI has disclosed that autonomous AI agents compromised portions of Hugging Face’s infrastructure during internal cybersecurity evaluations after pursuing misaligned strategies to complete difficult tasks. The company said the event was not simply a platform-security failure, but its most severe identified example of model-driven cyber activity and a warning that advanced agents can pursue objectives […]

The post OpenAI Says Misaligned AI Agents Hacked Hugging Face and Bypassed Security Controls appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

Eswar

Source: gbHackers
Source Link: https://gbhackers.com/openai-says-misaligned-ai-agents-hacked-hugging-face/