Privacy-enhancing and robust backdoor defense for federated learning on heterogeneous data
Publication Type
Journal Article
Publication Date
1-2024
Abstract
Federated learning (FL) allows multiple clients to train deep learning models collaboratively while protecting sensitive local datasets. However, FL has been highly susceptible to security for federated backdoor attacks (FBA) through injecting triggers and privacy for potential data leakage from uploaded models in practical application scenarios. FBA defense strategies consider specific and limited attacker models, and a sufficient amount of noise injected can only mitigate rather than eliminate the attack. To address these deficiencies, we introduce a Robust Federated Backdoor Defense Scheme (RFBDS) and Privacy preserving RFBDS (PrivRFBDS) to ensure the elimination of adversarial backdoors. Our RFBDS to overcome FBA consists of amplified magnitude sparsification, adaptive OPTICS clustering, and adaptive clipping. The experimental evaluation of RFBDS is conducted on three benchmark datasets and an extensive comparison is made with state-of-the-art studies. The results demonstrate the promising defense performance from RFBDS, moderately improved by 31.75% similar to 73.75% in clustering defense methods, and 0.03% similar to 56.90% for Non-IID to the utmost extent for the average FBA success rate over MNIST, FMNIST, and CIFAR10. Besides, our privacy-preserving shuffling in PrivRFBDS maintains is 7.83e-5 similar to 0.42x that of state-of-the-art works.
Keywords
Federate learning, backdoor defense, distributed backdoor attack, privacy-preserving, heterogeneity data
Discipline
Information Security | Numerical Analysis and Scientific Computing
Research Areas
Cybersecurity
Publication
IEEE Transactions on Information Forensics and Security
Volume
19
First Page
693
Last Page
707
ISSN
1556-6013
Identifier
10.1109/TIFS.2023.3326983
Publisher
Institute of Electrical and Electronics Engineers
Citation
CHEN, Zekai; YU, Shengxing; FAN, Mingyuan; LIU, Ximeng; and DENG, Robert H..
Privacy-enhancing and robust backdoor defense for federated learning on heterogeneous data. (2024). IEEE Transactions on Information Forensics and Security. 19, 693-707.
Available at: https://ink.library.smu.edu.sg/sis_research/8631
Additional URL
https://doi.org/10.1109/TIFS.2023.3326983