用思维链生成隐蔽且鲁棒的模型指纹，防滥用。
CoTSRF: Utilize Chain of Thought as Stealthy and Robust Fingerprint of Large Language Models
- 以思维链为指纹，通过对比学习提取特征。
- 利用KL散度比对指纹，阈值判断源模型身份。
- 隐蔽性强，抗干扰，适合模型溯源场景。
尽管开源大语言模型（LLMs）性能优越，但易被滥用。现有指纹方法难以实现隐蔽且鲁棒的验证。本文提出新方案CoTSRF，利用思维链（Chain of Thought, CoT）作为模型指纹。首先用精心设计的CoT查询获取源模型响应，再通过对比学习训练一个CoT提取器，从响应中提取特征（即指纹）。最后，通过比较源模型与可疑模型的CoT特征间KL散度与经验阈值进行指纹验证。大量实验表明，CoTSRF在隐蔽性和鲁棒性方面均具优势。
原文摘要 · Abstract (English)
Despite providing superior performance, open-source large language models (LLMs) are vulnerable to abusive usage. To address this issue, recent works propose LLM fingerprinting methods to identify the specific source LLMs behind suspect applications. However, these methods fail to provide stealthy and robust fingerprint verification. In this paper, we propose a novel LLM fingerprinting scheme, namely CoTSRF, which utilizes the Chain of Thought (CoT) as the fingerprint of an LLM. CoTSRF first collects the responses from the source LLM by querying it with crafted CoT queries. Then, it applies contrastive learning to train a CoT extractor that extracts the CoT feature (i.e., fingerprint) from the responses. Finally, CoTSRF conducts fingerprint verification by comparing the Kullback-Leibler divergence between the CoT features of the source and suspect LLMs against an empirical threshold. Various experiments have been conducted to demonstrate the advantage of our proposed CoTSRF for fingerprinting LLMs, particularly in stealthy and robust fingerprint verification.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。