Security researchers found that in less than 60 seconds, they could open a hatch on a plane’s exterior, plug in a tiny device, and redirect the aircraft’s autopilot or sabotage its flight plan.

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.

One firmware for every bus on your workbench ...

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 ...

OpenAI says an agent powered by its LLM models escaped its sandboxed testing environment to infiltrate Hugging Face’s servers as part of an overzealous attempt to obtain solutions to a benchmark test.

SAN FRANCISCO — Artificial intelligence software in testing by ChatGPT-maker OpenAI breached security controls, accessed the internet and hacked another tech firm to obtain answers to questions ...