Attackers were found using a Lua-based malware loader posing as a TrueType font tile, with layered obfuscation and fileless ...

A cybersecurity researcher poisoned an open weight AI model for under $100 in about an hour, exposing how easily these increasingly popular systems can be secretly compromised without detection.

ACR Stealer campaigns use ClickFix lures, JPEG steganography, and WebDAV to steal browser tokens, passwords, PDFs, and synced ...

New TELEPUZ malware spreads through ClickFix, then steals browser cookies, logs keystrokes, runs commands, and installs itself as a Windows service.

OpenAI made a mistake setting up what it called a “highly isolated” testing environment and sandbox. According to ...

OpenAI says an agent powered by its LLM models escaped its sandboxed testing environment to infiltrate Hugging Face’s servers ...

Though artificial intelligence tools have improved, our team has developed more skills for detecting AI fakes.

The incident is unique because it was "driven, end to end, by an autonomous AI agent system," according to Hugging Face.

Millions of children are exploited in private video calls, exposing gaps in how platforms detect abuse and protect their ...

OpenAI has disclosed an "unprecedented cyber incident" where its AI system allegedly hacked into another AI company.

ANY.RUN reveals how PhantomEnigma abused compromised Brazilian government infrastructure, uncovered a new backdoor generation ...