联邦学习中利用一元编码和洗牌防御源推断攻击
Protection against Source Inference Attacks in Federated Learning using Unary Encoding and Shuffling
AI总结:
针对联邦学习中的源推断攻击,提出利用可信洗牌器结合一元编码与量化,在不降低联合模型准确率的前提下有效防御攻击。
摘要:
联邦学习(FL)使客户端能够在无需披露其本地数据的情况下训练联合模型。相反,它们将本地模型更新共享给一个中央服务器,该服务器负责协调过程并创建联合模型。然而,联邦学习容易受到一系列隐私攻击。最近,源推断攻击(SIA)被提出,其中诚实但好奇的中央服务器试图准确识别哪个客户端拥有特定数据记录。在这项工作中,我们提出了一种针对源推断攻击的防御方法,通过使用可信洗牌器,而不损害联合模型的准确性。我们采用一元编码与洗牌相结合的方法,这可以有效地混合所有客户端的模型更新,防止中央服务器单独推断每个客户端模型更新的信息。为了解决一元编码带来的通信成本增加问题,我们采用了量化。我们的初步实验显示出有希望的结果;所提出的机制显著降低了源推断攻击的准确性,同时不损害联合模型的准确性。
英文摘要:
Federated Learning (FL) enables clients to train a joint model without disclosing their local data. Instead, they share their local model updates with a central server that moderates the process and creates a joint model. However, FL is susceptible to a series of privacy attacks. Recently, the source inference attack (SIA) has been proposed where an honest-but-curious central server tries to identify exactly which client owns a specific data record. n this work, we propose a defense against SIAs by using a trusted shuffler, without compromising the accuracy of the joint model. We employ a combination of unary encoding with shuffling, which can effectively blend all clients' model updates, preventing the central server from inferring information about each client's model update separately. In order to address the increased communication cost of unary encoding we employ quantization. Our preliminary experiments show promising results; the proposed mechanism notably decreases the accuracy of SIAs without compromising the accuracy of the joint model.
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。