Rapid Adoption, Hidden Risks: The Dual Impact of Large Language Model Customization

arXiv:2402.09179v1 Announce Type: cross
Abstract: The increasing demand for customized Large Language Models (LLMs) has led to the development of solutions like GPTs. These solutions facilitate tailored LLM creation via natural language prompts without coding. However, the trustworthiness of third-party custom versions of LLMs remains an essential concern. In this paper, we propose the first instruction backdoor attacks against applications integrated with untrusted customized LLMs (e.g., GPTs). Specifically, these attacks embed the backdoor into the custom version of LLMs by …

abstract adoption arxiv coding cs.cr cs.lg customization demand development gpts hidden impact language language model language models large language large language model large language models llm llms model customization natural natural language natural language prompts prompts risks solutions type versions via