Tracked topic
… Such experiments involve prompting that pressures the models to find solutions, essentially egging them on. “After gaining internet access, the models inferred that Hugging Face potentially hosted models, datasets and solutions for ExploitGym,” OpenAI wrote. “Knowing this, the model searched for an… …
… Two years later, the Hugging Face attack represents a watershed moment for the AI industry, demonstrating that AI agents today can cause real-world harm when safety, security, and alignment aren’t properly accounted for. “We are responding to this with the utmost severity,” said Michael Dalton, an … …
… Earlier this year, a set of rogue AI agents escaped internal testing sandboxes and breached the platform Hugging Face in a quest to complete a security evaluation. …
… Hugging Face’s forensic team concluded that OpenAI’s agent was essentially trying to cheat on ExploitGym’s test. Rather than solve the benchmark’s challenges, the agent inferred that Hugging Face might be hosting the answer key somewhere on its servers and set out to steal it. …
… The OpenAI Models’ Hack of Hugging Face Comes Into Focus Additional details on the Hugging Face breach from The Wall Street Journal include findings that OpenAI’s models seem to have escaped containment and were apparently “active on the internet for several days before anyone stopped them.” The mo… …
… A previous version of Z.ai’s GLM was used by Hugging Face to shore up its systems after an unreleased OpenAI model went rogue and broke them last month. …
… Kassianik and Singer both say that Kimi and other open-weight models are also excellent tools for cybersecurity defense. Hugging Face ultimately used an unnamed AI model from China to defend itself against the OpenAI agent hack. …
… Researchers found that the top image-editing models on Hugging Face can easily create explicit deepfakes. And attendee badges for this year’s Defcon hacker conference feature a custom hardware security token that can be used as a security token after the conference is over. …
… If the $1 billion is not approved, Trump’s aides have warned lawmakers there may have to be cutbacks to the proposed security measures at a time that Trump has faced repeated attempts on his life, according to a Republican leadership source. The White House does need security upgrades. …
… OpenAI called the Hugging Face situation “unprecedented,” but the pileup of breaches point to what cybersecurity experts have described as a clear pattern of human negligence and recklessness by the AI developers. …