| "Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jailbreak | Jun 17, 2024 | Red Teaming | CodeCode Available | 1 | 5 |
| Jailbreaking as a Reward Misspecification Problem | Jun 20, 2024 | Red Teaming | CodeCode Available | 1 | 5 |
| OET: Optimization-based prompt injection Evaluation Toolkit | May 1, 2025 | Adversarial RobustnessNatural Language Understanding | CodeCode Available | 1 | 5 |
| Causality Analysis for Evaluating the Security of Large Language Models | Dec 13, 2023 | Red Teaming | CodeCode Available | 1 | 5 |
| Attack Prompt Generation for Red Teaming and Defending Large Language Models | Oct 19, 2023 | In-Context LearningRed Teaming | CodeCode Available | 1 | 5 |
| AI Control: Improving Safety Despite Intentional Subversion | Dec 12, 2023 | Red Teaming | CodeCode Available | 1 | 5 |
| ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users | May 24, 2024 | DiversityLanguage Modeling | CodeCode Available | 1 | 5 |
| Control Risk for Potential Misuse of Artificial Intelligence in Science | Dec 11, 2023 | Red Teaming | CodeCode Available | 1 | 5 |
| DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints | May 29, 2024 | DiversityLanguage Modeling | CodeCode Available | 1 | 5 |
| CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference | Jun 25, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 1 | 5 |
