#Red Teaming

4 articles with this tag

AI Security Post-Codex & Claude: Kolter & Fredrikson
AI Research

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.

1 day ago
Securing AI Agents: A New Red Teaming Frontier
AI Research

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.

about 2 months ago
AI Agents on the Loose: Network Security Risks Emerge
AI Research

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.

about 2 months ago
AI Pen Testing: Open Source AI Finds 23 Flaws in Mock Network
Artificial Intelligence

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.

2 months ago