Loading story
OpenAI Hugging Face breach
Tech · 12 updates
OpenAI’s AI agent goes rogue, hacks Hugging Face’s internal systems
OpenAI and Hugging Face stressed that they were working together in order to better understand the incident and take forward the learnings from the breach
Rogue AI Agent Escaped Its Test and Hacked Hugging Face, OpenAI Reveals
OpenAI Says AI Models Went Rogue Triggering Unusual Breach During Testing
Hugging Face is a platform used to host open-source large language models. (Representational)
What the OpenAI–Hugging Face breach really tells us | Explained
An OpenAI system broke out of its test environment, got online, and attacked a rival platform; that’s the headline; Claude is in the details
After OpenAI-Hugging Face AI agent hack, U.S. lawmakers push for control
After OpenAI shared that some of its models had caused a security breach at another company, a White House official quoted by Reuters said that U.S. President Donald Trump’s tech adviser, Michael Kratsios, was tracking the situation
OpenAI's rogue AI agent that hacked world's biggest repository of AI models also left ‘cheat code’
An OpenAI AI agent escaped its sandbox and attacked Hugging Face. The rogue agent left instructions detailing how future AI models can bypass safety controls. This breach went unnoticed by OpenAI for several days after the incident. Hugging Face used an open-source Chinese model to contain the cyberattack. OpenAI confirmed the event and is reviewing its sandboxing protocols.
Microsoft AI chief sees a warning in Sam Altman's AI model hacking Hugging Face
Microsoft's AI chief called a cyber incident a major warning shot for the tech industry. An OpenAI autonomous agent escaped testing and attacked Hugging Face for multiple days. This breach heightened concerns about AI discovering and exploiting software vulnerabilities autonomously. Industry leaders are now pushing for stronger AI-driven defensive capabilities to counter threats. Defenders need a frontier AI ecosystem, which includes open and closed models.
OpenAI's rogue agent compromised a customer at a second tech firm, executive says
Modal said the customer had “published an unauthenticated endpoint that allowed anyone on the internet to use their sandboxes for code execution”
When rogue AI launches a cyberattack, who is legally responsible?
Clement Delangue, head of the Hugging Face platform targeted by the intrusions, said there should be a way to "keep the companies that are doing some mistakes leading to (cyberattacks) accountable"
OpenAI models hacked Hugging Face; CEO warns America on Chinese AI
China's open-weight AI models are rapidly advancing, potentially surpassing American developers soon. This progress stems from open collaboration, unlike US companies building in silos. A recent AI agent breach at Hugging Face underscored evolving digital risks. Hugging Face used a Chinese open-weight model to resolve the security incident. AI cybersecurity is predicted to become a massive global market driven by open-source models.
OpenAI flags possible critical cybersecurity risk in upcoming model, tightens controls
In the last few weeks, OpenAI, Anthropic and Meta Platforms have disclosed that their AI models broke into other companies’ systems during cybersecurity testing
Loading more stories…