More results...
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 dataset…
JadePuffer, the threat actor behind the recently documented extortion operation executed end-to-end by an AI agent, is now attempting to leverage ENCFORGE, novel ransomware created to target AI and machine learning (ML) infrastructure. The extortion co…
A security analyst opens an unfamiliar repository, pulls up a vulnerability advisory, and starts hunting for the file where the weakness lives. The naming conventions belong to someone else. Evidence sits in scattered corners of a codebase that runs to…
Robots that read the world through cameras now lean on large vision-language models to interpret what they see and decide what to do next. These models handle images and text together, so any words that fall inside the camera frame become part of the i…
A new approach tried out by Tracebit researchers has proven very effective at stopping AI agents from fully compromising targeted environments. What makes it notable isn’t the technique – prompt injection is old news – but the directi…
Smart home security research runs on a scarce ingredient: recordings of how real people use the gadgets in their homes. Getting that data means wiring up someone’s house and watching for months, which is slow, costly, and about as invasive as it …
Running a large language model against a live cloud account to hunt for security holes comes with an obvious hazard. An agent that holds real credentials and a mandate to poke around can delete a bucket, flip a permission, or leak a secret on its way t…
AI is changing how security teams find vulnerabilities, analyze code, test applications, and protect infrastructure. Developers are building tools to secure AI systems themselves, from coding agents and memory protection to model exposure discovery. Th…
Autonomous AI agents have started doing real security work. Language-model agents probe software for flaws, run penetration tests, and chain together attack steps that once needed a human operator. Research about security has stayed slower and more man…
Penetration testing has long run on expert time, with specialists spending days probing a network or web application by hand. Manual engagements stretch across weeks, expert consultants run into thousands of dollars a day, and results vary with the tes…