Has My System Prompt Been Used? Large Language Model Prompt Membership Inference
This addresses privacy concerns for organizations using proprietary prompts in LLMs, though it is incremental as it applies membership inference to a new context.
The paper tackles the problem of protecting proprietary system prompts in large language models by developing Prompt Detective, a statistical method for prompt membership inference that reliably determines if a specific prompt was used, achieving verification with statistical significance.
Prompt engineering has emerged as a powerful technique for optimizing large language models (LLMs) for specific applications, enabling faster prototyping and improved performance, and giving rise to the interest of the community in protecting proprietary system prompts. In this work, we explore a novel perspective on prompt privacy through the lens of membership inference. We develop Prompt Detective, a statistical method to reliably determine whether a given system prompt was used by a third-party language model. Our approach relies on a statistical test comparing the distributions of two groups of model outputs corresponding to different system prompts. Through extensive experiments with a variety of language models, we demonstrate the effectiveness of Prompt Detective for prompt membership inference. Our work reveals that even minor changes in system prompts manifest in distinct response distributions, enabling us to verify prompt usage with statistical significance.