Red-Teaming for Generative AI: Silver Bullet or Security Theater

Is generative-AI red teaming a rigorous practice or a compliance exercise?

Key findings

Surveyed practices show inconsistent threat models, evaluators and disclosure - Proposes a question bank to structure red-teaming reports

Spot an error, or know a record we should add? Members can propose additions and submit corrections.

Results of the largest public agent red-teaming competition, showing universal vulnerability of frontier agents to human-crafted injections.

Community infrastructure for reproducible jailbreak evaluation, with an evolving repository of attack artefacts and a leaderboard.

The standard benchmark for automated red teaming, used to compare jailbreak methods and to train more robust refusal behaviour.