Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack

arXiv:2404.01833v1 Announce Type: new
Abstract: Large Language Models (LLMs) have risen significantly in popularity and are increasingly being adopted across multiple applications. These LLMs are heavily aligned to resist engaging in illegal or unethical topics as a means to avoid contributing to responsible AI harms. However, a recent line of attacks, known as "jailbreaks", seek to overcome this alignment. Intuitively, jailbreak attacks aim to narrow the gap between what the model can do and what it is willing to do. …

applications article arxiv attack cs.ai cs.cr great illegal jailbreak language language models large llm llms responsible responsible ai topics turn