Red Teaming
EvaluationactiveAdversarial testing of AI systems to discover failure modes, both manual and automated.
Organizations
3
Risks Addressed
1
Cluster: Evaluation
Parent Area: AI Evaluations
Tags
function:assurancescope:sub-field
Organizations3
| Organization | Role |
|---|---|
| Anthropic | active |
| Google DeepMind | active |
| OpenAI | active |
Sub-Areas1
| Name | Status | Orgs | Papers |
|---|---|---|---|
| Jailbreak ResearchFinding, categorizing, and patching prompt injection and jailbreak attacks. | active | 0 | 0 |