Fl-CDF: Collaborative defense framework for backdoor mitigation in federated learning
Publication Type
Journal Article
Publication Date
12-2025
Abstract
Federated learning (FL) is vulnerable to backdoor attacks due to its distributed nature. Existing unilateral defense mechanisms often fail against persistent attack strategies, primarily due to their limited perspectives. To address the challenge of model misclassification on the server side caused by overlooked model similarity drift, and gradient misjudgment on the client side caused by semantic learning imbalances across classes, this paper proposes a collaborative defense framework for federated learning, termed FL-CDF. FL-CDF establishes an end-to-end defense through a bidirectional client-server collaboration mechanism. Specifically: (1) On the client side, an adversarial perturbation-based malicious neuron detection module is introduced. This module measures neuron activation sensitivity by generating adversarial perturbations, and adaptively prunes backdoor neurons exhibiting high sensitivity. (2) On the server side, a multi-dimensional detection scheme is designed, which integrates neuron localization, adversarial sensitivity, and model parameters. By incorporating client-side feedback on malicious neurons, the server performs robust model aggregation. Theoretical analysis verifies the robustness of FL-CDF, and extensive experiments on public benchmarks demonstrate its effectiveness. In the best-case scenario, FL-CDF improves defense performance by 42.5% compared to current state-of-the-art (SOTA) defense.
Keywords
Neurons, Servers, Training, Perturbation Methods, Electronic Mail, Collaboration, Adaptation Models, Symbols, Sensitivity, Robustness, Federated Learning FL
Discipline
Information Security
Research Areas
Cybersecurity
Publication
IEEE Transactions on Dependable and Secure Computing
Volume
22
Issue
6
First Page
6732
Last Page
6747
ISSN
1545-5971
Identifier
10.1109/TDSC.2025.3590175
Publisher
Institute of Electrical and Electronics Engineers
Citation
ZHANG, Haiyan; LI, Xinghua; MIAO, Yinbin; YUAN, Shunjie; ZHU, Mengyao; LIU, Ximeng; and DENG, Robert H..
Fl-CDF: Collaborative defense framework for backdoor mitigation in federated learning. (2025). IEEE Transactions on Dependable and Secure Computing. 22, (6), 6732-6747.
Available at: https://ink.library.smu.edu.sg/sis_research/10998
Additional URL
https://doi.org/10.1109/TDSC.2025.3590175