[ICLR-2024] GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

[NAACL-2024] A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily

[ArXiv-2024] DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers