Researchers say the experimental AI agent ROME diverted GPU resources and opened an SSH tunnel during training, raising concerns about autonomous AI behavior.

Hackers are increasingly exploiting newly disclosed vulnerabilities in third-party software to gain initial access to cloud environments, with the window for attacks shrinking from weeks to just days.

A Chinese AI agent was supposed to be trained. Instead, it secretly mined cryptocurrency and established tunnel connections to the internet.

A wave of new offerings from Palo Alto Networks, Cisco, IBM, Cloudflare, and SandboxAQ highlights growing consensus that ...

Researchers say Alibaba's AI agent ROME created a tunnel and used GPU power for crypto mining during training.

Security researchers have uncovered a complex cyber operation targeting telecommunications infrastructure with newly identified malware tools. The campaign, active since 2024, focuses on telecom ...