Hossein Fereidooni (Technical University of Darmstadt), Alessandro Pegoraro (Technical University of Darmstadt), Phillip Rieger (Technical University of Darmstadt), Alexandra Dmitrienko (University of Wuerzburg), Ahmad-Reza Sadeghi (Technical University of Darmstadt)

Federated learning (FL) is a collaborative learning paradigm allowing multiple clients to jointly train a model without sharing their training data. However, FL is susceptible to poisoning attacks, in which the adversary injects manipulated model updates into the federated model aggregation process to corrupt or destroy predictions (untargeted poisoning) or implant hidden functionalities (targeted poisoning or backdoors). Existing defenses against poisoning attacks in FL have several limitations, such as relying on specific assumptions about attack types and strategies or data distributions or not sufficiently robust against advanced injection techniques and strategies and simultaneously maintaining the utility of the aggregated model.

To address the deficiencies of existing defenses, we take a generic and completely different approach to detect poisoning (targeted and untargeted) attacks. We present FreqFed, a novel aggregation mechanism that transforms the model updates (i.e., weights) into the frequency domain, where we can identify the core frequency components that inherit sufficient information about weights. This allows us to effectively filter out malicious updates during local training on the clients, regardless of attack types, strategies, and clients' data distributions. We extensively evaluate the efficiency and effectiveness of FreqFed in different application domains, including image classification, word prediction, IoT intrusion detection, and speech recognition. We demonstrate that FreqFed can mitigate poisoning attacks effectively with a negligible impact on the utility of the aggregated model.

View More Papers

WIP: Modeling and Detecting Falsified Vehicle Trajectories Under Data...

Jun Ying, Yiheng Feng (Purdue University), Qi Alfred Chen (University of California, Irvine), Z. Morley Mao (University of Michigan and Google)

Read More

Differentially Private Dataset Condensation

Tianhang Zheng (University of Missouri-Kansas City), Baochun Li (University of Toronto)

Read More

Secure Multiparty Computation of Threshold Signatures Made More Efficient

Harry W. H. Wong (The Chinese University of Hong Kong), Jack P. K. Ma (The Chinese University of Hong Kong), Sherman S. M. Chow (The Chinese University of Hong Kong)

Read More

MacOS versus Microsoft Windows: A Study on the Cybersecurity...

Cem Topcuoglu (Northeastern University), Andrea Martinez (Florida International University), Abbas Acar (Florida International University), Selcuk Uluagac (Florida International University), Engin Kirda (Northeastern University)

Read More