| Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs) | Jul 20, 2024 | Red Teaming | CodeCode Available | 1 |
| CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference | Jun 25, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 1 |
| Jailbreaking as a Reward Misspecification Problem | Jun 20, 2024 | Red Teaming | CodeCode Available | 1 |
| Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner | Jun 17, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 1 |
| "Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jailbreak | Jun 17, 2024 | Red Teaming | CodeCode Available | 1 |
| MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models | Jun 11, 2024 | Red Teaming | CodeCode Available | 1 |
| Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits | Jun 3, 2024 | Red Teaming | CodeCode Available | 1 |
| DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints | May 29, 2024 | DiversityLanguage Modeling | CodeCode Available | 1 |
| Learning diverse attacks on large language models for robust red-teaming and safety tuning | May 28, 2024 | DiversityLanguage Modeling | CodeCode Available | 1 |
| ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users | May 24, 2024 | DiversityLanguage Modeling | CodeCode Available | 1 |
