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 2409.19988cs.CR
收藏

在隐私保护联邦学习中使用随机二值权重增强安全性

Enhancing Security Using Random Binary Weights in Privacy-Preserving Federated Learning

Hiroto Sawada, Shoko Imaizumi, Hitoshi Kiya

AI总结:

本文提出在联邦学习中由各客户端用独立二值随机数序列乘以更新信息后再上传,从而在不降低模型性能的同时增强对数据猜测攻击的鲁棒性,并通过实验验证其对APRIL恢复攻击的抵抗效果。

摘要:

本文提出了一种利用视觉Transformer(Vision Transformer)增强隐私保护联邦学习安全性的新方法。在联邦学习中,学习过程通过收集更新信息来进行,而无需收集每个客户端的原始数据。然而,问题在于,原始数据可能从更新信息中被推断出来。针对这一问题,传统的数据猜测对策(安全增强方法)在隐私保护强度与学习效率之间存在权衡关系,并且通常会降低模型性能。本文提出了一种新的联邦学习方法,该方法不会降低模型性能,并且对针对更新信息的数据猜测攻击具有鲁棒性。在所提出的方法中,每个客户端独立准备一个二值(0或1)随机数序列,将其与更新信息相乘,然后发送到服务器用于模型学习。在实验中,从模型性能和对APRIL(Attention PRIvacy Leakage)恢复攻击的抵抗能力两方面确认了所提方法的有效性。

英文摘要:

In this paper, we propose a novel method for enhancing security in privacy-preserving federated learning using the Vision Transformer. In federated learning, learning is performed by collecting updated information without collecting raw data from each client. However, the problem is that this raw data may be inferred from the updated information. Conventional data-guessing countermeasures (security enhancement methods) for addressing this issue have a trade-off relationship between privacy protection strength and learning efficiency, and they generally degrade model performance. In this paper, we propose a novel method of federated learning that does not degrade model performance and that is robust against data-guessing attacks on updated information. In the proposed method, each client independently prepares a sequence of binary (0 or 1) random numbers, multiplies it by the updated information, and sends it to a server for model learning. In experiments, the effectiveness of the proposed method is confirmed in terms of model performance and resistance to the APRIL (Attention PRIvacy Leakage) restoration attack.

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。

↑