FLAIRS: FPGA-Accelerated Inference-Resistant & Secure Federated Learning

Conference Paper (2023)
Author(s)

Huimin Li (TU Delft - Cyber Security)

Phillip Rieger (Technische Universität Darmstadt)

Shaza Zeitouni (Technische Universität Darmstadt)

S. Picek (Radboud Universiteit Nijmegen, TU Delft - Cyber Security)

Ahmad Reza Sadeghi (Technische Universität Darmstadt)

Research Group
Cyber Security
Copyright
© 2023 H. Li, Phillip Rieger, Shaza Zeitouni, S. Picek, Ahmad Reza Sadeghi
DOI related publication
https://doi.org/10.1109/FPL60245.2023.00046
More Info
expand_more
Publication Year
2023
Language
English
Copyright
© 2023 H. Li, Phillip Rieger, Shaza Zeitouni, S. Picek, Ahmad Reza Sadeghi
Research Group
Cyber Security
Pages (from-to)
271-276
ISBN (print)
979-8-3503-4152-2
ISBN (electronic)
979-8-3503-4151-5
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Federated Learning (FL) has become very popular since it enables clients to train a joint model collaboratively without sharing their private data. However, FL has been shown to be susceptible to backdoor and inference attacks. While in the former, the adversary injects manipulated updates into the aggregation process; the latter leverages clients' local models to deduce their private data. Contemporary solutions to address the security concerns of FL are either impractical for real-world deployment due to high-performance overheads or are tailored towards addressing specific threats, for instance, privacy-preserving aggregation or backdoor defenses. Given these limitations, our research delves into the advantages of harnessing the FPGA-based computing paradigm to overcome performance bottlenecks of software-only solutions while mitigating backdoor and inference attacks. We utilize FPGA-based enclaves to address inference attacks during the aggregation process of FL. We adopt an advanced backdoor-aware aggregation algorithm on the FPGA to counter backdoor attacks. We implemented and evaluated our method on Xilinx VMK-180, yielding a significant speed-up of around 300 times on the IoT-Traffic dataset and more than 506 times on the CIFAR-10 dataset.

Files

FLAIRS_FPGA_Accelerated_Infere... (pdf)
(pdf | 0.336 Mb)
- Embargo expired in 02-05-2024
License info not available