All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks

Large Language Models (LLMs), such as ChatGPT, encounter `jailbreak' challenges, wherein safeguards are circumvented to generate ethically harmful prompts. This study introduces a straightforward black-box method for efficiently crafting jailbreak prompts, addressing the significant complexity and computational costs associated with conventional methods. Our technique iteratively transforms harmful prompts into benign expressions directly utilizing the target LLM, predicated on the hypothesis that LLMs can autonomously generate expressions that evade safeguards. Through experiments conducted with ChatGPT (GPT-3.5 and GPT-4) and Gemini-Pro, our …

attacks box challenges chatgpt complexity computational costs cs.ai cs.cl cs.cy generate jailbreak language language models large language large language models llms prompts safeguards simple study