OpenAI's Hugging Face attack postmortem shows agents don't care about rules — they need strong controls.

A threat actor used a variety of infostealers to collect session information and access Claude accounts belonging to an ...

The ClickFix-style campaign features a sophisticated, multistage attack chain that includes reverse tunnels into victim ...

The campaign uses EtherHiding to dynamically update its command-and-control server, using the blockchain as an ...

While guardrails are critical, as evidenced by recent high-profile incidents, defenders need help staying ahead of attackers ...

James Kettle of PortSwigger talks with the Dark Reading News Desk about his AI-powered open source tool, which found new HTTP ...

Omdia's Theresa Lanowitz talks with the Dark Reading News Desk about the potential — and risks — of using agentic AI for ...

This installment of the Reporters' Notebook video series discusses several topics such as AI's effects on vulnerability ...

While these dynamics will always be true for OT, defenders are getting help from cyber deception as it matures beyond ...

North Korean operatives posing as IT workers are improving their tactics, but researchers say there are still ways to spot ...

The Hugging Face incident was bigger and worse than previously thought, with around 700 agents collaborating on a ...

Attackers can exploit a flaw in NVIDIA's tool to gain access to the local model server through the Ollama API paving the way ...