An AI agent executed the technical part of a ransomware attack for the first time. However, a human was still involved in selecting the target, setting up infrastructure, and providing stolen credentials. This means the attack was not fully autonomous as initially reported.
Source preview
Server-side extracted preview paragraphs from the original source.
An AI agent carried out the technical execution of a real-world ransomware attack for the first known time, but new details show a human still chose the victim, set up the infrastructure, and supplied stolen credentials — meaning it wasn't quite the fully...
Last week, researchers at cloud security firm Sysdig said they’d documented the first known case of “agentic ransomware.” It was an extortion operation, dubbed JadePuffer, in which an AI agent — not a human — handled the technical execution of a real-world...