AI-built ransomware toolkit automates EDR evasion, AD discovery

A threat actor is using an AI-built ransomware attack toolkit that automates Active Directory discovery and helps evade ...
CSO Online

Hugging Face Transformers RCE flaw enables stealthy compromise via AI model configs

With over 2.2 billion installs, the flawed Python package offers attackers a huge blast radius, including silent access to ...
Bleeping Computer

ChatGPT share links abused to host fake outage pages to deliver malware

Threat actors are abusing ChatGPT's content-sharing feature to display fake OpenAI outage pages that direct users to download malware disguised as the ChatGPT desktop application. The "LLMShare" ...

Modders are turning Ray-Ban Meta glasses into spy gear for as little as $50

Modders are charging $50-$100 to physically destroy the LED on Ray-Ban Meta smart glasses and bypass privacy guardrails for ...
Decrypt

What Is an AI Prompt Injection Attack? The Hidden Threat Hijacking Your Chatbots

Hackers can hijack ChatGPT, Claude, and Gemini with nothing but a sentence. OpenAI says the problem may never be fully solved.

These AI models are free, private, and will never say 'no'

Open-weight AI models with advanced capabilities and no safeguards are becoming much more accessible. While they can be ...