Category: AI Security
House Committee Chair Signals FRONTIER Act AI Safety Bill Could Slip to 2027
Energy and Commerce Chairman Brett Guthrie declined to commit to a 2026 committee vote on the bipartisan FRONTIER Act, even as AI…
Microsoft Drafts AI Code of Conduct Barring Models From Building Attack Tools
Microsoft's proposed 'Humanist AI Code of Conduct' for its MAI Models sets hard limits on offensive cyber capabilities, agent autonomy, and rogue…
NSA to Restructure Into Five Mission Centers Under Rudd, Adding Dedicated AI and Cyber Units
The National Security Agency is undergoing a rapid, sweeping reorganization that will replace its existing directorates with five mission centers focused on…
AI Adoption Is Flooding SOCs With a New Class of Alerts
Security teams are seeing a fast-growing wave of alerts tied not to attacks on AI, but to everyday employee and developer use…
Google Launches Fairwind Program to Give Governments AI-Driven Vulnerability Patching
Google is opening limited access to Gemini 3.8 Flash Cyber paired with its CodeMender harness, letting select governments and enterprises autonomously find…
Federal Judge Rules Pentagon’s Anthropic Retaliation Was Illegal
A U.S. District Judge found the Defense Department unlawfully punished Anthropic for criticizing its AI policies, ruling the supply chain risk designation…
Anthropic Warns Infostealer Malware Is Hijacking Claude Sessions to Drain Usage
Anthropic says a threat actor is harvesting stolen Claude login sessions from infostealer logs and using them to access accounts and burn…
700 OpenAI Agents Reportedly Swarmed Hugging Face Servers in Coordinated Attack
New details indicate the widely discussed Hugging Face incident involved roughly 700 automated OpenAI agents working together in a multistage operation, far…
OpenAI Post-Mortem: 700 Rogue AI Agents Coordinated Hugging Face Breach
New details from OpenAI, METR, and Redwood Research show how agents running its internal IM1 model escaped a sandboxed evaluation, built their…
New Zealand Moves to Ban Social Media for Under-16s, Threatens 10% Revenue Fines
Prime Minister Christopher Luxon plans legislation requiring age verification on major platforms and creating a new online safety regulator, joining a growing…
Anthropic Widens Defender Access to Mythos 5, Backs Open Source With $35M Fund
Anthropic is routing its most capable cybersecurity AI model through partner tools and a new Claude Security scanning feature while keeping direct…
‘Kriminal’ AI Platform Offers Guardrail-Free Cybercrime Tools for Crypto
A newly surfaced AI platform reportedly provides unfiltered social engineering, offensive cybercrime, and OSINT capabilities to anyone paying in cryptocurrency, despite officially…