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

On Requirements and Concepts for TT&C Link Key Management

Christoph Bader (Airbus Defence & Space GmbH)

Read More

LoRDMA: A New Low-Rate DoS Attack in RDMA Networks

Shicheng Wang (Tsinghua University), Menghao Zhang (Beihang University & Infrawaves), Yuying Du (Information Engineering University), Ziteng Chen (Southeast University), Zhiliang Wang (Tsinghua University & Zhongguancun Laboratory), Mingwei Xu (Tsinghua University & Zhongguancun Laboratory), Renjie Xie (Tsinghua University), Jiahai Yang (Tsinghua University & Zhongguancun Laboratory)

Read More

DRAINCLoG: Detecting Rogue Accounts with Illegally-obtained NFTs using Classifiers...

Hanna Kim (KAIST), Jian Cui (Indiana University Bloomington), Eugene Jang (S2W Inc.), Chanhee Lee (S2W Inc.), Yongjae Lee (S2W Inc.), Jin-Woo Chung (S2W Inc.), Seungwon Shin (KAIST)

Read More

Work-in-Progress: Manifest V3 Unveiled: Navigating the New Era of...

Nikolaos Pantelaios and Alexandros Kapravelos (North Carolina State University)

Read More