Enhanced Model Poisoning Attack and Multi-Strategy Defense in Federated Learning
Top Cited Papers
- 26 March 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 20 (15566013) , 3877-3892
Abstract
As a new paradigm of distributed learning, Federated Learning (FL) has been applied in industrial fields, such as intelligent retail, finance and autonomous driving. However, several schemes that aim to attack robust aggregation rules and reducing the model accuracy have been proposed recently. These schemes do not maintain the sign statistics of gradients unchanged during attacks. Therefore, the sign statistics-based scheme SignGuard can resist most existing attacks. To defeat SignGuard and most existing cosine or distance-based aggregation schemes, we propose an enhanced model poisoning attack, ScaleSign. Specifically, ScaleSign uses a scaling attack and a sign modification component to obtain malicious gradients with higher cosine similarity and modify the sign statistics of malicious gradients, respectively. In addition, these two components have the least impact on the magnitudes of gradients. Then, we propose MSGuard, a Multi-Strategy Byzantine-robust scheme based on cosine mechanisms, symbol statistics, and spectral methods. Formal analysis proves that malicious gradients generated by ScaleSign have a closer cosine similarity than honest gradients. Extensive experiments demonstrate that ScaleSign can attack most of the existing Byzantine-robust rules, especially achieving a success rate of up to 98.23% for attacks on SignGuard. MSGuard can defend against most existing attacks including ScaleSign. Specifically, in the face of ScaleSign attack, the accuracy of MSGuard improves by up to 41.78% compared to SignGuard.Keywords
Funding Information
- National Key Research and Development Program of China (2024YFB3108700)
- Shaanxi Fundamental Science Research Project for Mathematics and Physics (22JSY019)
- National Natural Science Foundation of China (62125205, U23A20303)
- Opening Project of Intelligent Policing Key Laboratory of Sichuan Province (ZNJW2023KFMS002)
- Open fund of Key Laboratory of Computing Power Network and Information Security (2023ZD020)
This publication has 16 references indexed in Scilit:
- Covert Model Poisoning Against Federated Learning: Algorithm Design and OptimizationIEEE Transactions on Dependable and Secure Computing, 2023
- Model poisoning attack in differential privacy-based federated learningInformation Sciences, 2023
- Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering2022
- MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clients2022
- FedRecAttack: Model Poisoning Attack to Federated Recommendation2022
- ShieldFL: Mitigating Model Poisoning Attacks in Privacy-Preserving Federated LearningIEEE Transactions on Information Forensics and Security, 2022
- Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferability2021
- Deep Residual Learning for Image Recognition2016
- Deep learningNature, 2015
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998