Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
10-2025
Abstract
As a distributed machine learning paradigm, Federated Learning (FL) enables large-scale clients to collaboratively train a model without sharing their raw data. However, due to the lack of data auditing for untrusted clients, FL is vulnerable to poisoning attacks, especially backdoor attacks. By using poisoned data for local training or directly changing the model parameters, attackers can easily inject backdoors into the model, which can trigger the model to make misclassification of targeted patterns in images. To address these issues, we propose a novel data-free trigger-generation-based defense approach based on the two characteristics of backdoor attacks: i) triggers are learned faster than normal knowledge, and ii) trigger patterns have a greater effect on image classification than normal class patterns. Our approach generates the images with newly learned knowledge by identifying the differences between the old and new global models, and filters trigger images by evaluating the effect of these generated images. By using these trigger images, our approach eliminates poisoned models to ensure the updated global model is benign. Comprehensive experiments demonstrate that our approach can defend against almost all the existing types of backdoor attacks and outperform all the seven state-of-the-art defense methods with both IID and non-IID scenarios. Especially, our approach can successfully defend against the backdoor attack even when 80\% of the clients are malicious.
Keywords
Federated learning, backdoor defense, conditional generative ad-versarial network, data-free, knowledge filtering
Discipline
Artificial Intelligence and Robotics | Databases and Information Systems
Research Areas
Intelligent Systems and Optimization
Areas of Excellence
Digital transformation
Publication
CCS '25: Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security, Taipei, Taiwan, October 13-17
First Page
3147
Last Page
3161
Identifier
10.1145/3719027.3744883
Publisher
ACM
City or Country
New York
Citation
YANG, Yanxin; HU, Ming; XIE, Xiaofei; CAO, Yue; ZHANG, Pengyu; HUANG, Yihao; and CHEN, Mingsong.
FilterFL: Knowledge filtering-based data-free backdoor defense for federated learning. (2025). CCS '25: Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security, Taipei, Taiwan, October 13-17. 3147-3161.
Available at: https://ink.library.smu.edu.sg/sis_research/10634
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/10.1145/3719027.3744883