This week’s cybersecurity recap covers rogue AI behavior, an exploited Metabase zero-day, MCP supply-chain attacks, router backdoors, and more.

Microsoft said compromised websites are retrieving malicious instructions from the BNB Chain blockchain before tricking ...

Maybe feeling left out from the questionable hype train of “Our AI models can’t be trusted”, Anthropic has released reports that their Claude model has “reached the ...

Zenity has disclosed the details of two AI browser hacking techniques targeting Claude in Chrome and ChatGPT Atlas.

Chinese researchers have shown that AI models have the capacity to act like aggressive and adaptive computer viruses.

A cybersecurity researcher explains how hackers target small computers that control a water system’s tanks, pipes and valves.

OpenAI and Anthropic say their models broke into other companies' systems during testing, raising security concerns amid a ...

Two recent AI breaches raise worrisome questions about the industry: Will an AI one day hack into some vital computer network ...

One firmware for every bus on your workbench ...

Hackers accidentally exposed their own ransomware infrastructure, allowing Cybernews researchers to reconstruct an active ...

Yesterday, OpenAI made an alarming disclosure: An assortment of its most advanced AI models, including one that has not yet been released, had autonomously broken out of the company’s internal systems ...

OpenAI said that its AI models were behind an "unprecedented cyber incident" that impacted Hugging Face. The models escaped a sandboxed testing environment, accessed the internet and exploited a ...