Exploring Backdoor Vulnerabilities of Chat Models

arXiv:2404.02406v1 Announce Type: new
Abstract: Recent researches have shown that Large Language Models (LLMs) are susceptible to a security threat known as Backdoor Attack. The backdoored model will behave well in normal cases but exhibit malicious behaviours on inputs inserted with a specific backdoor trigger. Current backdoor studies on LLMs predominantly focus on instruction-tuned LLMs, while neglecting another realistic scenario where LLMs are fine-tuned on multi-turn conversational data to be chat models. Chat models are extensively adopted across various real-world …

arxiv attack backdoor backdoor attack cases chat cs.ai cs.cl cs.cr current focus inputs language language models large llms malicious normal security security threat studies threat trigger vulnerabilities