FP-VEC: Fingerprinting Large Language Models via Efficient Vector Addition

arXiv - CS - Cryptography and Security Pub Date : 2024-09-13 DOI:arxiv-2409.08846

Zhenhua Xu, Wenpeng Xing, Zhebo Wang, Chang Hu, Chen Jie, Meng Han

引用次数: 0

Abstract

Training Large Language Models (LLMs) requires immense computational power and vast amounts of data. As a result, protecting the intellectual property of these models through fingerprinting is essential for ownership authentication. While adding fingerprints to LLMs through fine-tuning has been attempted, it remains costly and unscalable. In this paper, we introduce FP-VEC, a pilot study on using fingerprint vectors as an efficient fingerprinting method for LLMs. Our approach generates a fingerprint vector that represents a confidential signature embedded in the model, allowing the same fingerprint to be seamlessly incorporated into an unlimited number of LLMs via vector addition. Results on several LLMs show that FP-VEC is lightweight by running on CPU-only devices for fingerprinting, scalable with a single training and unlimited fingerprinting process, and preserves the model's normal behavior. The project page is available at https://fingerprintvector.github.io .

查看原文本刊更多论文

FP-VEC：通过高效向量加法对大型语言模型进行指纹识别

训练大型语言模型（LLM）需要巨大的计算能力和海量数据。因此，通过指纹识别来保护这些模型的知识产权对于所有权认证至关重要。虽然已经有人尝试通过微调来为 LLM 添加指纹，但这仍然成本高昂且不可扩展。在本文中，我们介绍了 FP-VEC，这是一项将指纹向量用作 LLM 高效指纹识别方法的试验性研究。我们的方法生成的指纹矢量代表了嵌入模型的机密签名，通过矢量添加，同一指纹可以无缝地集成到数量不限的 LLM 中。在多个 LLM 上的研究结果表明，FP-VEC 只需在 CPU 设备上运行即可进行指纹识别，具有轻量级特点，只需一次训练和无限次指纹识别过程即可扩展，并能保留模型的正常行为。项目页面：https://fingerprintvector.github.io 。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

arXiv - CS - Cryptography and Security

自引率

0.00%

发文量