AI agent security now has a purpose-built open-source guardrail: Ant Group released SingGuard-NSFA, a free framework that catches prompt injection and credential-theft patterns before AI agents ...
In its first "state of open-source AI" report, the Firefox maker lays out its vision of an AI industry that doesn't belong to ...
The new release was delayed after the U.S. government restricted the latest artificial intelligence models over cybersecurity ...
a laptop screen with a webpage of the IT Army of Ukraine group of volunteer hackers. The IT Army of Ukraine first set up in the wake of Russia's devastating attack, and has since hugely grown in ...
Chinese AI company Z.ai released an open-weight model, dubbed GLM-5.2, which experts warn could be just as dangerous as ...
Researchers have detected what is likely the first instance of a ransomware attack—dubbed JadePuffer—led entirely by an ...
Researchers have spotted likely the first case of a ransomware attack, called JadePuffer, led entirely by an AI agent, sparking fears over the future of cybersecurity. However, there may be a twist.
An AI agent carried out the technical execution of a real-world ransomware attack for the first known time, but new details ...
JadePuffer, the first known 'agentic ransomware', uses an AI agent to run attacks end-to-end and adapt in real time, ...
The Agentic AI Foundation has taken in its first project since launch. CTO Manik Surtani explains why an open, portable ...
Security researchers have identified JadePuffer, the first ransomware attack which is filly executed by an autonomous AI ...