FP-VEC:通过高效向量加法对大型语言模型进行指纹识别

Zhenhua Xu, Wenpeng Xing, Zhebo Wang, Chang Hu, Chen Jie, Meng Han
{"title":"FP-VEC:通过高效向量加法对大型语言模型进行指纹识别","authors":"Zhenhua Xu, Wenpeng Xing, Zhebo Wang, Chang Hu, Chen Jie, Meng Han","doi":"arxiv-2409.08846","DOIUrl":null,"url":null,"abstract":"Training Large Language Models (LLMs) requires immense computational power\nand vast amounts of data. As a result, protecting the intellectual property of\nthese models through fingerprinting is essential for ownership authentication.\nWhile adding fingerprints to LLMs through fine-tuning has been attempted, it\nremains costly and unscalable. In this paper, we introduce FP-VEC, a pilot\nstudy on using fingerprint vectors as an efficient fingerprinting method for\nLLMs. Our approach generates a fingerprint vector that represents a\nconfidential signature embedded in the model, allowing the same fingerprint to\nbe seamlessly incorporated into an unlimited number of LLMs via vector\naddition. Results on several LLMs show that FP-VEC is lightweight by running on\nCPU-only devices for fingerprinting, scalable with a single training and\nunlimited fingerprinting process, and preserves the model's normal behavior.\nThe project page is available at https://fingerprintvector.github.io .","PeriodicalId":501332,"journal":{"name":"arXiv - CS - Cryptography and Security","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"FP-VEC: Fingerprinting Large Language Models via Efficient Vector Addition\",\"authors\":\"Zhenhua Xu, Wenpeng Xing, Zhebo Wang, Chang Hu, Chen Jie, Meng Han\",\"doi\":\"arxiv-2409.08846\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Training Large Language Models (LLMs) requires immense computational power\\nand vast amounts of data. As a result, protecting the intellectual property of\\nthese models through fingerprinting is essential for ownership authentication.\\nWhile adding fingerprints to LLMs through fine-tuning has been attempted, it\\nremains costly and unscalable. In this paper, we introduce FP-VEC, a pilot\\nstudy on using fingerprint vectors as an efficient fingerprinting method for\\nLLMs. Our approach generates a fingerprint vector that represents a\\nconfidential signature embedded in the model, allowing the same fingerprint to\\nbe seamlessly incorporated into an unlimited number of LLMs via vector\\naddition. Results on several LLMs show that FP-VEC is lightweight by running on\\nCPU-only devices for fingerprinting, scalable with a single training and\\nunlimited fingerprinting process, and preserves the model's normal behavior.\\nThe project page is available at https://fingerprintvector.github.io .\",\"PeriodicalId\":501332,\"journal\":{\"name\":\"arXiv - CS - Cryptography and Security\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Cryptography and Security\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.08846\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Cryptography and Security","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.08846","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

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。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
FP-VEC: Fingerprinting Large Language Models via Efficient Vector Addition
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 .
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
PAD-FT: A Lightweight Defense for Backdoor Attacks via Data Purification and Fine-Tuning Artemis: Efficient Commit-and-Prove SNARKs for zkML A Survey-Based Quantitative Analysis of Stress Factors and Their Impacts Among Cybersecurity Professionals Log2graphs: An Unsupervised Framework for Log Anomaly Detection with Efficient Feature Extraction Practical Investigation on the Distinguishability of Longa's Atomic Patterns
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1