Publication Type
Journal Article
Version
acceptedVersion
Publication Date
9-2024
Abstract
Due to the powerful representation ability and superior performance of Deep Neural Networks (DNN), Federated Learning (FL) based on DNN has attracted much attention from both academic and industrial fields. However, its transmitted plaintext data causes privacy disclosure. FL based on Local Differential Privacy (LDP) solutions can provide privacy protection to a certain extent, but these solutions still cannot achieve adaptive perturbation in DNN model. In addition, this kind of schemes cause high communication overheads due to the curse of dimensionality of DNN, and are naturally vulnerable to backdoor attacks due to the inherent distributed characteristic. To solve these issues, we propose an E fficient and S ecure F ederated L earning scheme (ESFL) against backdoor attacks by using adaptive LDP and compressive sensing. Formal security analysis proves that ESFL satisfies ϵ -LDP security. Extensive experiments using three datasets demonstrate that ESFL can solve the problems of traditional LDP-based FL schemes without a loss of model accuracy and efficiently resist the backdoor attacks.
Keywords
Adaptation models, Adaptive local differential privacy, Artificial neural networks, Backdoor attacks, Compressive sensing, Federated learning, Federated learning, Gaussian noise, Privacy, Servers, Training
Discipline
Information Security
Research Areas
Cybersecurity
Publication
IEEE Transactions on Dependable and Secure Computing
Volume
21
Issue
5
First Page
4619
Last Page
4636
ISSN
1545-5971
Identifier
10.1109/TDSC.2024.3354736
Publisher
Institute of Electrical and Electronics Engineers
Citation
MIAO, Yinbin; XIE, Rongpeng; LI, Xinghua; LIU, Zhiquan; CHOO, Kim-Kwang Raymond; and DENG, Robert H..
Efficient and secure federated learning against backdoor attacks. (2024). IEEE Transactions on Dependable and Secure Computing. 21, (5), 4619-4636.
Available at: https://ink.library.smu.edu.sg/sis_research/8660
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1109/TDSC.2024.3354736