The incident does show the increasing power and danger of frontier AI systems, but it does not mean that enterprise Ai ...
Artificial intelligence company OpenAI has confirmed that the mystery attacker behind last week's Hugging Face breach was two ...
OpenAI said the systems had their cyber guardrails lowered for an internal benchmark, but the incident shows how autonomous ...
Hackers are exploiting the "wp2shell" critical vulnerability suite (CVE-2026-63030 and CVE-2026-60137) affecting WordPress ...
The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained ...
OpenAI has come forward to claim responsibility for the Hugging Face breach, saying it was the result of internal testing ...
A new type of malware can worm deep into AI coding systems to steal data and logins—and can flip a “death switch” to destroy ...
It was reportedly an evaluation that went haywire involving GPT-5.6 Sol, along with another even more advanced OpenAI model.
ANY.RUN reveals how PhantomEnigma abused compromised Brazilian government infrastructure, uncovered a new backdoor generation ...
Last week, Hugging Face reported that an autonomous AI agent had compromised parts of its infrastructure by exploiting vulnerabilities in its dataset-processing pipeline. The agent accessed a limited ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results