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 2312.06989cs.CR
收藏

面向联邦学习、抵御属性推断攻击的任务无关隐私保护表示学习

Task-Agnostic Privacy-Preserving Representation Learning for Federated Learning Against Attribute Inference Attacks

Caridad Arroyo Arevalo, Sayedeh Leila Noorbakhsh, Yun Dong, Yuan Hong, Binghui Wang

AI总结:

本文提出任务无关的 TAPPFL 框架,通过双互信息目标学习少含敏感属性、多保留任务效用的表示,并给出可证明隐私保证。

摘要:

联邦学习(FL)近来得到广泛研究,因为它能够在不共享原始数据的情况下,协同训练来自不同设备的数据。然而,近期研究表明,攻击者仍有可能推断出设备数据中的隐私信息,例如收入、种族和性取向等敏感属性。为缓解属性推断攻击,可以采用或改造多种现有隐私保护 FL 方法。但这些现有方法都存在关键局限:它们需要提前知道 FL 任务,或者具有难以承受的计算开销或效用损失,或者不具备可证明的隐私保证。我们解决了这些问题,并设计了一种用于 FL、抵御属性推断攻击的任务无关隐私保护表示学习方法(TAPPFL)。TAPPFL 通过信息论形式化。具体而言,TAPPFL 具有两个互信息目标:一个目标学习任务无关的数据表示,使其包含尽可能少的、关于每个设备数据中私有属性的信息;另一个目标确保所学数据表示包含尽可能多的、关于设备数据的信息,以维持 FL 效用。我们还推导了 TAPPFL 针对最坏情况属性推断攻击的隐私保证,以及效用保持与隐私保护之间固有的权衡。在多个数据集和应用上的大量结果验证了 TAPPFL 在保护数据隐私、维持 FL 效用以及保持高效方面的有效性。实验结果还表明,TAPPFL 优于现有防御方法(源代码和完整版本见 https://github.com/TAPPFL)。

英文摘要:

Federated learning (FL) has been widely studied recently due to its property to collaboratively train data from different devices without sharing the raw data. Nevertheless, recent studies show that an adversary can still be possible to infer private information about devices' data, e.g., sensitive attributes such as income, race, and sexual orientation. To mitigate the attribute inference attacks, various existing privacy-preserving FL methods can be adopted/adapted. However, all these existing methods have key limitations: they need to know the FL task in advance, or have intolerable computational overheads or utility losses, or do not have provable privacy guarantees. We address these issues and design a task-agnostic privacy-preserving presentation learning method for FL ({\bf TAPPFL}) against attribute inference attacks. TAPPFL is formulated via information theory. Specifically, TAPPFL has two mutual information goals, where one goal learns task-agnostic data representations that contain the least information about the private attribute in each device's data, and the other goal ensures the learnt data representations include as much information as possible about the device data to maintain FL utility. We also derive privacy guarantees of TAPPFL against worst-case attribute inference attacks, as well as the inherent tradeoff between utility preservation and privacy protection. Extensive results on multiple datasets and applications validate the effectiveness of TAPPFL to protect data privacy, maintain the FL utility, and be efficient as well. Experimental results also show that TAPPFL outperforms the existing defenses\footnote{Source code and full version: \url{https://github.com/TAPPFL}}.

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。

↑