On the Efficiency of Privacy Attacks in Federated Learning

Abstract

<p>Recent studies have revealed severe privacy risks in fed- erated learning, represented by Gradient Leakage Attacks. However, existing studies mainly aim at increasing the pri- vacy attack success rate and overlook the high computa- tion costs for recovering private data, making the privacy attack impractical in real applications. In this study, we examine privacy attacks from the perspective of efficiency and propose a framework for improving the Efficiency of Privacy Attacks in Federated Learning (EPAFL). We make three novel contributions. First, we systematically evaluate the computational costs for representative privacy attacks in federated learning, which exhibits a high potential to op- timize efficiency. Second, we propose three early-stopping techniques to effectively reduce the computational costs of these privacy attacks. Third, we perform experiments on benchmark datasets and show that our proposed method can significantly reduce computational costs and maintain comparable attack success rates for state-of-the-art privacy attacks in federated learning.</p>