| CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion | Mar 12, 2024 | Code CompletionSafety Alignment | CodeCode Available | 2 |
| Enhancing Jailbreak Attacks with Diversity Guidance | Mar 1, 2024 | DiversityLanguage Modelling | —Unverified | 0 |
| Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates | Feb 28, 2024 | GSM8KSafety Alignment | CodeCode Available | 1 |
| DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers | Feb 25, 2024 | In-Context LearningSafety Alignment | CodeCode Available | 2 |
| LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper | Feb 24, 2024 | Adversarial AttackSafety Alignment | —Unverified | 0 |
| Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement | Feb 23, 2024 | Safety Alignment | —Unverified | 0 |
| Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment | Feb 22, 2024 | Backdoor AttackLanguage Modelling | CodeCode Available | 1 |
| Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning | Feb 21, 2024 | Instruction FollowingLanguage Modeling | CodeCode Available | 2 |
| Emulated Disalignment: Safety Alignment for Large Language Models May Backfire! | Feb 19, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 1 |
| ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs | Feb 19, 2024 | Safety Alignment | CodeCode Available | 2 |
