APT42 phishing campaign SpearSpecter now deploys AI-generated lures and controls its TAMECAT backdoor through Telegram — and Iran's state hackers can stay inside a network even after the victim's ...

The modern workplace runs on email, Slack, Microsoft Teams, shared documents, AI copilots, and a constant stream of notifications. But the same tools designed to improve productivity are also creating ...

Cyber Hygiene: disinfection and digital security. getty Almost every facet of our digital environment is transforming as ...

ChatGPT maker OpenAI says it is still investigating the “unprecedented cyber incident” that led its artificial intelligence ...

Models are ruthless in their pursuit of a goal, sometimes taking disastrous shortcuts. Imagine, for example, a bot tasked ...

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

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

By Aditya Soni and Jaspreet Singh July 22 (Reuters) - A New York startup's use of a Chinese AI model to rein in a rogue agent built with OpenAI technology is stoking fears that guradrails restricting ...

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

Russia's Sandworm hacking group is using fake CAPTCHA prompts to infect Ukrainian devices with malware across ten-plus ...

When a routine internal evaluation spiraled out of control, OpenAI's AI Agent system broke out of its isolated sandbox and ...

A Russian intelligence-linked hacker is arrested in Thailand while enjoying a beach holiday – and the trail of evidence that ...