The recent Hugging Face breach was the work of several OpenAI models, the AI research company claimed in a blog post. The breach Late last week, the company behind Hugging Face, a platform that enables users to share machine learning models and datasets, said some of its internal datasets had been accessed without authorization. The attack vector was, according to Hugging Face, a malicious dataset that exploited code-execution paths in the company’s dataset processing pipeline, … More
The post OpenAI: Our models breached Hugging Face during a cyber capability test appeared first on Help Net Security.
source & further reading
helpnetsecurity.com — original article
OpenAI Presence connects AI agents to enterprise data with built-in guardrails
Astelia extends reachability analysis with agentic AI for vulnerability management
ThreatDown expands security visibility to AI tools and machine identities