| PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling | Feb 4, 2025 | Safety Alignment | CodeCode Available | 0 |
| Internal Activation as the Polar Star for Steering Unsafe LLM Behavior | Feb 3, 2025 | Safety Alignment | —Unverified | 0 |
| The dark deep side of DeepSeek: Fine-tuning attacks against the safety alignment of CoT-enabled models | Feb 3, 2025 | Safety Alignment | —Unverified | 0 |
| LLM Safety Alignment is Divergence Estimation in Disguise | Feb 2, 2025 | Language ModelingLanguage Modelling | CodeCode Available | 0 |
| Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning | Jan 31, 2025 | BlockingSafety Alignment | —Unverified | 0 |
| Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation | Jan 30, 2025 | Safety Alignment | CodeCode Available | 1 |
| Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation | Jan 29, 2025 | Red TeamingSafety Alignment | CodeCode Available | 2 |
| xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking | Jan 28, 2025 | Reinforcement Learning (RL)Safety Alignment | CodeCode Available | 1 |
| Towards Safe AI Clinicians: A Comprehensive Study on Large Language Model Jailbreaking in Healthcare | Jan 27, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models | Jan 23, 2025 | Safety Alignment | —Unverified | 0 |
