#Red Teaming
5 articles with this tag
OpenAI's GPT-Red: AI Learns to Police Itself
OpenAI's new GPT-Red system uses AI to find and fix vulnerabilities, making models like GPT-5.6 Sol significantly more robust against attacks.
AI Security Post-Codex & Claude: Kolter & Fredrikson
AI security experts Zico Kolter & Matt Fredrikson discuss the challenges posed by models like Codex & Claude, and Gray Swan's approach to securing AI.
Securing AI Agents: A New Red Teaming Frontier
A new AI red teaming platform, DTap, and its autonomous agent DTap-Red are introduced to systematically evaluate and secure AI agents across diverse real-world domains.
AI Agents on the Loose: Network Security Risks Emerge
Microsoft Research reveals how AI agents interacting at scale create new security risks like worms, reputation manipulation, and invisible attacks.
AI Pen Testing: Open Source AI Finds 23 Flaws in Mock Network
IBM security experts discussed an experiment where the AI agent OpenClaw found 23 vulnerabilities in a mock network, highlighting AI's potential and challenges in cybersecurity.