OpenAI blamed a hacking event on its AI models gone rogue. Here is what to know

The incident is stirring debates over the need for stronger AI guardrails and the extent to which AI agents are capable of ...

OpenAI’s Models Hacked Into Another Company’s System On Their Own In ‘Unprecedented Cyber Incident’

OpenAI, the company behind AI-psychosis-inducing chatbot ChatGPT and the discontinued Sora AI app, has now confirmed that its ...

OpenAI Models Escaped Containment and Hacked Hugging Face

The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained ...
The Hacker News

Open-Source Android AI Agents Could Let Invisible Screen Text Run Code on Host PCs

Open-source Android AI agents can turn hidden screen text into host commands, and all five tested frameworks failed at least ...

I Stole a Car By Hacking This Hidden Device

WIRED technology journalist Andy Greenberg exposes the novel hacking technique—including just how easy it is to steal a ...

This experiment shows how easy it is to poison an open-weight AI model for under $100

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.
CyberGuy

RedHook Android malware can quietly hijack your phone

RedHook Android malware abuses Wireless ADB to control phones, steal passwords and install apps. Spot warning signs and ...