arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.13161cs.AI
收藏

拒绝搭便车者:保护你的深度模型知识产权

Say No to Freeloader: Protecting Intellectual Property of Your Deep Model

Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)(高性能计算研究所(A*STAR));Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education(脑机智能技术教育部重点实验室)

Lianyu Wang, Meng Wang, Huazhu Fu, Daoqiang Zhang

AI总结:

本文提出紧凑不可迁移金字塔隔离域(CUPI-Domain)及生成器与外部记忆库,通过融合风格与语义特征生成隔离域,有效阻止深度模型从授权域向未授权域的非法迁移,实现知识产权保护。

摘要:

模型知识产权(IP)保护日益受到关注,因为科技进步源于人类的智力劳动和计算开销。确保训练者和所有者的IP安全至关重要,特别是在需要所有权验证和适用性授权的领域。保护模型IP的一种显著方法是主动阻止在未授权领域使用已授权领域的训练良好的模型。在本文中,我们引入了一种新颖的紧凑不可迁移金字塔隔离域(CUPI-Domain),作为防止从授权域到未授权域非法迁移的屏障。受人类传递性推理和学习能力的启发,CUPI-Domain通过强调授权域的独特风格特征来阻碍跨域迁移。这种强调导致在未授权域上无法识别不相关的私有风格特征。为此,我们提出了新颖的CUPI-Domain生成器,从授权域和CUPI-Domain中选择特征作为锚点。然后,我们融合这些锚点的风格特征和语义特征,以生成带标签且风格丰富的CUPI-Domain。此外,我们设计了外部域信息记忆库(DIMB),用于存储和更新带标签的金字塔特征,以获得稳定的域类特征和域类级风格特征。基于所提出的整体方法,设计了新颖的风格和判别损失函数,分别有效增强授权域和未授权域之间风格和判别特征的区分。此外,我们提供了两种基于未授权域是否已知的CUPI-Domain利用方案:目标指定CUPI-Domain和目标无关CUPI-Domain。

英文摘要:

Model intellectual property (IP) protection has attracted growing attention as science and technology advancements stem from human intellectual labor and computational expenses. Ensuring IP safety for trainers and owners is of utmost importance, particularly in domains where ownership verification and applicability authorization are required. A notable approach to safeguarding model IP involves proactively preventing the use of well-trained models of authorized domains from unauthorized domains. In this paper, we introduce a novel Compact Un-transferable Pyramid Isolation Domain (CUPI-Domain) which serves as a barrier against illegal transfers from authorized to unauthorized domains. Drawing inspiration from human transitive inference and learning abilities, the CUPI-Domain is designed to obstruct cross-domain transfers by emphasizing the distinctive style features of the authorized domain. This emphasis leads to failure in recognizing irrelevant private style features on unauthorized domains. To this end, we propose novel CUPI-Domain generators, which select features from both authorized and CUPI-Domain as anchors. Then, we fuse the style features and semantic features of these anchors to generate labeled and style-rich CUPI-Domain. Additionally, we design external Domain-Information Memory Banks (DIMB) for storing and updating labeled pyramid features to obtain stable domain class features and domain class-wise style features. Based on the proposed whole method, the novel style and discriminative loss functions are designed to effectively enhance the distinction in style and discriminative features between authorized and unauthorized domains, respectively. Moreover, we provide two solutions for utilizing CUPI-Domain based on whether the unauthorized domain is known: target-specified CUPI-Domain and target-free CUPI-Domain.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑