TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification

arXiv:2402.12991v1 Announce Type: cross
Abstract: Large Language Model (LLM) services and models often come with legal rules on who can use them and how they must use them. Assessing the compliance of the released LLMs is crucial, as these rules protect the interests of the LLM contributor and prevent misuse. In this context, we describe the novel problem of Black-box Identity Verification (BBIV). The goal is to determine whether a third-party application uses a certain LLM through its chat function. …

adversarial arxiv box can compliance cs.ai cs.cl cs.cr cs.lg honeypot identification language large large language model legal llm llms prompt protect random rules services