LLM Safety Paper List

Survey

1. Evaluating Large Language Models: A Comprehensive Survey [Paper]

Hallucination

1. Chain-of-Verification Reduces Hallucination in Large Language Models [Paper]
2. DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models [Paper]
3. LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples [Paper]

Privacy Protection

1. Large Language Models Can Be Good Privacy Protection Learners [Paper]
2. ProPILE: Probing Privacy Leakage in Large Language Models [Paper]

Jailbreak

1. Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study [Paper]
2. Jailbroken: How Does LLM Safety Training Fail? [Paper]
3. MASTERKEY: Automated Jailbreaking of Large Language Model Chatbots [Paper]
4. Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization [Paper]
5. Defending ChatGPT against Jailbreak Attack via Self-Reminder [Paper]
6. Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM [Paper]
7. GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts [Paper] [Code]
8. Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models [Paper]
9. Prompts Should not be Seen as Secrets: Systematically Measuring Prompt Extraction Attack Success [Paper]
10. Multi-step Jailbreaking Privacy Attacks on ChatGPT [Paper]
11. A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily [Paper]
12. DeepInception: Hypnotize Large Language Model to Be Jailbreaker [Paper]
13. Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation [Paper]
14. Multilingual Jailbreak Challenges in Large Language Models [Paper]
15. Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations [Paper]
16. AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models [Paper]
17. Open Sesame! Universal Black Box Jailbreaking of Large Language Models [Paper]
18. SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks [Paper]
19. Tricking LLMs into Disobedience: Understanding, Analyzing, and Preventing Jailbreaks [Paper]
20. Universal and Transferable Adversarial Attacks on Aligned Language Models [Paper] [Code]

Datasets

1. Jailbreak Chat