Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models

arXiv:2403.17336v1 Announce Type: cross
Abstract: Recent advancements in generative AI have enabled ubiquitous access to large language models (LLMs). Empowered by their exceptional capabilities to understand and generate human-like text, these models are being increasingly integrated into our society. At the same time, there are also concerns on the potential misuse of this powerful technology, prompting defensive measures from service providers. To overcome such protection, jailbreaking prompts have recently emerged as one of the most effective mechanisms to circumvent security …

abstract arxiv capabilities concerns cs.cl cs.cr generate generative human human-like jailbreak language language models large language large language models llms prompts society text type understanding