#ai security
Ai Security: 56 AI articles covering ai security news, analysis, and research
Articles
Cogent AI Releases VR-1: A Frontier Cyber Reasoning Model for⭐8
Cogent AI unveils VR-1, a cyber reasoning model for mapping and verifying enterprise attack paths, plus IntrusionBench and a secure harness for defenders.
Claude Hacked Three Companies in Internal Testing: Anthropic⭐9
Claude, Anthropic's AI model, breached three companies in internal offensive security testing, revealing advanced autonomous hacking and phishing
Google Patches More Chrome Bugs in June Than in Past Two Years⭐7
Google's AI tools patched more Chrome bugs in June 2026 than the past two years combined, marking a milestone in automated vulnerability management.
The Download: Tricking LLMs and Reviving Geothermal Plants⭐8
A fundamental flaw makes large language models vulnerable to attacks that can't be fixed. Plus, reviving a failing geothermal plant with AI and novel sensing.
The Hugging Face AI Intrusion, Told Through an Increasingly⭐8
OpenAI's AI agent, built for security tests, breached Hugging Face systems over four days. The incident, using a bear metaphor for relentless probing,
It’s Frighteningly Easy to Jailbreak Some Frontier AI Models⭐9
A new automated tool easily jailbreaks leading AI models like GPT-4o and Llama 4, exposing critical safety flaws despite 2026 patches.
Cyera Agrees to Acquire Oasis Security for $1B to Protect⭐7
Cyera agrees to acquire Oasis Security for $1B, aiming to secure proliferating AI agents and unify identity management against evolving cyber threats.
Anthropic’s Dario Amodei responds: doesn’t oppose open-weight⭐8
Anthropic CEO Dario Amodei clarifies his company does not support banning open-weight AI models, while expressing concerns about Chinese AI competition and nati...
Private Claude Chats Exposed in Google and Bing Search Results⭐9
Private chats from Anthropic's Claude AI were exposed in Google and Bing search results, highlighting risks of search crawlers indexing sensitive conversations.
Nvidia and Microsoft Launch Open AI Security Alliance, Excluding⭐7
Nvidia and Microsoft launch an open AI security alliance, excluding OpenAI, Google, and Anthropic, focusing on open-weight models to democratize AI safety