Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs

arXiv:2406.09324v1 Announce Type: new
Abstract: Although Large Language Models (LLMs) have demonstrated significant capabilities in executing complex tasks in a zero-shot manner, they are susceptible to jailbreak attacks and can be manipulated to produce harmful outputs. Recently, a growing body of research has categorized jailbreak attacks into token-level and prompt-level attacks. However, previous work primarily overlooks the diverse key factors of jailbreak attacks, with most studies concentrating on LLM vulnerabilities and lacking exploration of defense-enhanced LLMs. To address these issues, …

arxiv attacks benchmarking cs.ai cs.cl cs.cr jailbreak llms tricks