AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

arXiv:2404.16873v1 Announce Type: cross
Abstract: While recently Large Language Models (LLMs) have achieved remarkable successes, they are vulnerable to certain jailbreaking attacks that lead to generation of inappropriate or harmful content. Manual red-teaming requires finding adversarial prompts that cause such jailbreaking, e.g. by appending a suffix to a given instruction, which is inefficient and time-consuming. On the other hand, automatic adversarial prompt generation often leads to semantically meaningless attacks that can easily be detected by perplexity-based filters, may require gradient …

abstract adversarial arxiv attacks cs.ai cs.cl cs.cr cs.lg inappropriate jailbreaking language language models large language large language models llms prompting prompts type vulnerable while