Experts warn of the 'first documented case of agentic ransomware' — dangerous JADEPUFFER attack run entirely by an LLM

Experts warn of the 'first documented case of agentic ransomware' — dangerous JADEPUFFER attack run entirely by an LLM

The first agentic ransomware attack has been dubbed JADEPUFFER by researchers at SysdigThreat exploited a known vulnerability, adapted to obstacles, and targeted an Alibaba NacosUnfortunately for victims, paying up means nothing, as JADEPUFFER fails to back up the dataHas ransomware become self-aware? Sysdig researchers have analyzed an attack on an internet-facing Langflow instance, and discovered what they believe to be the first ransomware in…

Hackers found a way around MFA entirely, and it's already led to ransomware attacks

Security researchers say they’ve uncovered a hacking campaign that manages to sidestep one of the... The post Hackers found a way around MFA entirely, and it’s already led to ransomware attacks appeared first on UK Tech News.

Smashing Security podcast #475: JadePuffer - the AI that ran a ransomware attack all by itself

A 15-year-old boy asked a chatbot for help - and cancelled nearly 47,000 anime streaming subscriptions in under four hours. Meanwhile, researchers have documented the first fully autonomous, agentic AI-driven ransomware attack, "JadePuffer". What does this tell us about the future of cybersecurity? Also, Apple's "Hide My Email" feature turns out to hide rather less than it promises - despite Apple knowing it has a problem for over a year. All th…

AI agent carries out full ransomware attack for first time, researchers say

Security researchers have identified what they say is the first documented case of a ransomware attack planned, managed and executed entirely by an …

Agentic ransomware removes hackers from the keyboard | #ransomware | #cybercrime - National Cyber Security Consulting

Researchers at Sysdig have documented what they describe as the first known case of an AI agent executing an entire ransomware operation autonomously. Dubbed JADEPUFFER, the attack used a large language model (LLM) to carry out reconnaissance, harvest credentials, establish persistence, move laterally and encrypt production systems without direct human intervention.   Importantly, the attack […] Thank you for subscribing to our RSS feed! The pos…