AdaptPrint: Response-Adaptive Fingerprinting of Black-Box LLM Services

2026-08-23

AI Summary

为解决黑盒LLM服务的安全风险评估和版权审核问题，提出AdaptPrint方法，通过三种响应一致性探测策略识别模型身份。

Abstract

Black-box LLM services have emerged as a practical deployment paradigm. Nevertheless, their opacity also hinders the systematic assessment of security risks and complicates copyright auditing for model owners. Black-box LLM fingerprinting, which identifies the underlying LLM identity through query-response interactions, offers a promising way to bridge this gap. Existing approaches typically collect responses from target LLM services using a fixed set of queries and perform poorly in the presence of realistic and complex configurations (e.g., system prompt and sampling settings). To overcome these limitations, we propose AdaptPrint, a response-adaptive fingerprinting method for revealing hidden LLM identities in black-box LLM services. AdaptPrint integrates three progressive response consistency probing strategies: Direct Probing, Continuation Probing, and Follow-up Probing. AdaptPrint determines the final LLM identity by performing similarity matching among candidate LLMs. Experimental results show that AdaptPrint significantly outperforms state-of-the-art methods among 27 candidate models, achieving Top-1, Top-3, and Top-5 accuracies of 80.6%, 90.3%, and 92.1%. AdaptPrint also demonstrates strong robustness across different defense strategies and decoding parameters.

Problem

• black-box LLM
• security risks
• copyright auditing
• fingerprinting
• response consistency

Innovation

• response-adaptive fingerprinting
• black-box LLM services
• consistency probing strategies
• similarity matching