Prompt Injection attack against LLM-integrated Applications

arXiv:2306.05499v2 Announce Type: replace
Abstract: Large Language Models (LLMs), renowned for their superior proficiency in language comprehension and generation, stimulate a vibrant ecosystem of applications around them. However, their extensive assimilation into various services introduces significant security risks. This study deconstructs the complexities and implications of prompt injection attacks on actual LLM-integrated applications. Initially, we conduct an exploratory analysis on ten commercial applications, highlighting the constraints of current attack strategies in practice. Prompted by these limitations, we subsequently formulate HouYi, …

applications arxiv attack attacks complexities cs.ai cs.cl cs.cr cs.se ecosystem injection injection attack injection attacks language language models large llm llms prompt prompt injection prompt injection attacks risks security security risks services study