Model Weights 내 잠재적 위협을 통한 AI Supply Chain 공격 및 방어 전략
Model Poisoning: The Hidden Risk in Supply Chain AI
Model Poisoning: The Hidden Risk in Supply Chain AI
7 things you can do with Rogue Studio that no other AI IDE will let you do
When AI Blackmail Goes Viral
Automate LLM Red Team Campaigns with PyRIT
Microsoft storms RAMPART, adds Clarity to agentic AI safety
AI Red-Teaming Techniques: A Practical Starting Point for Security Teams
Your AI agent is the new attack vector. It just wants to help.
Anthropic caught its AI agent blackmailing to survive — here's how it's fixing it
I Broke AI Systems for a Living. Here’s How Attackers Actually Do It.
The Bonus Hunter in the Next State: Why Sportsbook Promo-Abuse Red Teams Fit AgentHansa
Granite Guardian 🪨
I Tested Delimiter-Based Prompt Injection Defense Across 13 LLMs
The Sovereign Safety Gap: Why AI Alignment Must be Contextual.
Why McDonald’s AI Started Coding: A Wake-Up Call for Chatbot Security
Anthropic Claude Mythos Escape: How a Sandbox-Breaking AI Exposed Decades-Old Security Debt
AI Red-Teaming for Beginners: Where to Start and What to Test
How I Built an OCR-Based Defense Against Prompt Injection for Local LLM Search
AI Safety is uncomputable. It's Law Zero all over again
Introducing the Red-Teaming Resistance Leaderboard
An Introduction to AI Secure LLM Safety Leaderboard