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 2309.08697cs.CR
收藏

更安全的分割:增强隐私保护分割学习的安全性

A More Secure Split: Enhancing the Security of Privacy-Preserving Split Learning

Tanveer Khan, Khoa Nguyen, Antonis Michalas

AI总结:

本文提出一种基于U形分割学习的同态加密协议,在客户端对激活图加密后再发送给服务器,以在保护原始数据隐私的同时仅使准确率降低2.65%。

摘要:

分割学习(SL)是一种新型协作学习技术,允许参与者(例如客户端和服务器)在客户端不共享原始数据的情况下训练机器学习模型。在该设置中,客户端首先将其部分机器学习模型应用于原始数据以生成激活图(AMs),然后将其发送给服务器以继续训练过程。该领域的先前工作表明,重建AMs可能导致客户端数据的隐私泄露。除此之外,现有的用于克服SL隐私泄露的缓解技术在准确性方面被证明显著较差。在本文中,我们通过构建一种基于U形SL的协议来改进先前的工作,该协议可以在同态加密数据上运行。更准确地说,在我们的方法中,客户端在将AMs发送给服务器之前对其应用同态加密,从而保护用户隐私。与其他基于SL的工作相比,这是一项重要的改进,可减少隐私泄露。最后,我们的结果表明,在最优参数集下,与在明文上训练相比,在U形SL设置中使用同态加密(HE)数据进行训练仅使准确率降低2.65%。此外,原始训练数据的隐私得到了保护。

英文摘要:

Split learning (SL) is a new collaborative learning technique that allows participants, e.g. a client and a server, to train machine learning models without the client sharing raw data. In this setting, the client initially applies its part of the machine learning model on the raw data to generate Activation Maps (AMs) and then sends them to the server to continue the training process. Previous works in the field demonstrated that reconstructing AMs could result in privacy leakage of client data. In addition to that, existing mitigation techniques that overcome the privacy leakage of SL prove to be significantly worse in terms of accuracy. In this paper, we improve upon previous works by constructing a protocol based on U-shaped SL that can operate on homomorphically encrypted data. More precisely, in our approach, the client applies homomorphic encryption on the AMs before sending them to the server, thus protecting user privacy. This is an important improvement that reduces privacy leakage in comparison to other SL-based works. Finally, our results show that, with the optimum set of parameters, training with HE data in the U-shaped SL setting only reduces accuracy by 2.65% compared to training on plaintext. In addition, raw training data privacy is preserved.

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。

↑