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

arXiv:2402.09179v1 Announce Type: new
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 …

adoption arxiv coding cs.cr cs.lg customization demand development gpts hidden impact language language models large large language model led llm llms natural natural language party prompts rapid risks solutions third third-party trustworthiness