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 2303.10399cs.CRcs.AI
收藏

FedRight:一种有效的联邦学习模型版权保护

FedRight: An Effective Model Copyright Protection for Federated Learning

Zhejiang University of Technology(浙江工业大学);TÜV SÜD Asia Pacific Pte. Ltd.(南德意志集团亚太私人有限公司)

Jinyin Chen, Mingjun Li, Mingjun Li, Haibin Zheng

摘要:

联邦学习(FL)是一种有效的分布式机器学习框架,它在实现模型训练的同时保护本地数据隐私。由于其良好的性能和可观的经济效益,它已被广泛应用于各种实践领域。模型归谁所有,如何保护版权已成为一个现实问题。直观地说,现有的集中式场景下的产权保护方法(例如,水印嵌入和模型指纹)是FL的可能解决方案。但是它们仍然受到FL在无数据共享、参数聚集和联邦训练设置方面的分布式特性的挑战。本文首次对FL的版权保护问题进行了形式化描述,提出了基于模型指纹的FedRight模型版权保护方法,即:通过生成对抗性示例作为模型指纹来提取模型特征。FedRight在四个关键方面优于以前的工作:(i)有效性:它提取模型特征生成可转移的指纹,训练检测器来验证模型的版权。(ii)保真度:它对联邦训练的影响是不可感知的,从而保证了良好的主任务性能。(iii)鲁棒性:它对版权保护的恶意攻击具有经验鲁棒性,即,微调、模型修剪和自适应攻击。(iv)黑盒:它在黑盒取证场景中有效,其中只有对模型的应用程序编程接口调用可用。对3个数据集和9个模型结构的广泛评估证明了FedRight卓越的保真度,有效性和鲁棒性。

英文摘要:

Federated learning (FL), an effective distributed machine learning framework, implements model training and meanwhile protects local data privacy. It has been applied to a broad variety of practice areas due to its great performance and appreciable profits. Who owns the model, and how to protect the copyright has become a real problem. Intuitively, the existing property rights protection methods in centralized scenarios (e.g., watermark embedding and model fingerprints) are possible solutions for FL. But they are still challenged by the distributed nature of FL in aspects of the no data sharing, parameter aggregation, and federated training settings. For the first time, we formalize the problem of copyright protection for FL, and propose FedRight to protect model copyright based on model fingerprints, i.e., extracting model features by generating adversarial examples as model fingerprints. FedRight outperforms previous works in four key aspects: (i) Validity: it extracts model features to generate transferable fingerprints to train a detector to verify the copyright of the model. (ii) Fidelity: it is with imperceptible impact on the federated training, thus promising good main task performance. (iii) Robustness: it is empirically robust against malicious attacks on copyright protection, i.e., fine-tuning, model pruning, and adaptive attacks. (iv) Black-box: it is valid in the black-box forensic scenario where only application programming interface calls to the model are available. Extensive evaluations across 3 datasets and 9 model structures demonstrate FedRight's superior fidelity, validity, and robustness.

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。

↑