Evaluating Security and Robustness for Split Federated Learning Against Poisoning Attacks
- 4 November 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 20 (15566013) , 175-190
Abstract
Split federated learning (SFL) is a recently proposed distributed collaborative learning architecture that integrates federated learning (FL) with split learning (SL), offering an ingenious solution for safeguarding privacy in resource-limited environments. Despite the compelling potential of SFL and its appealing attributes, its robustness remains uncharted territory. In this paper, we investigate the security and robustness of SFL, with a specific focus on its susceptibility to malicious client-driven poisoning attacks. Specifically, we study the weaknesses of SFL against the well-known poisoning attacks designed for FL, like dataset poisoning, weight poisoning, and label poisoning. We also introduce a novel type of poisoning attacks tailored for SFL, named smash poisoning, and evaluate the robustness against smash poisoning attacks and advanced hybrid attacks (DatasetSmash, LabelSmash, and WeightSmash) that amalgamate smash poisoning with the other three methods for FL. By simulating these attacks across diverse domains over four datasets, we find that most of these attacks (including weight, WeightSmash, and LabelSmash poisoning) can disrupt the converged models with straightforward poisoning actions or have persistent negative influence on the model accuracy even after the termination of the attacks. Furthermore, our findings reveal that the robustness of SFL can be augmented by strategically adjusting the system parameters, such as client quantity, bottleneck size, or split type. Finally, we verify the effectiveness of the typical defense mechanisms of poisoning attacks intended for FL and design a new defense strategy that filters out malicious smashed data to improve the robustness of SFL. We observe that the adoption of properly chosen defense mechanisms is beneficial in decreasing the security risks of SFL, but entirely eliminating the impacts of poisoning attacks in SFL is still challenging.Keywords
This publication has 17 references indexed in Scilit:
- Poisoning Online Learning Filters by Shifting on the Move2023
- Fortifying Federated Learning against Membership Inference Attacks via Client-level Input Perturbation2023
- Benchmarking the Effect of Poisoning Defenses on the Security and Bias of Deep Learning Models2023
- Data Poisoning Attack by Label Flipping on SplitFed Learning2023
- Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learning2022
- ShieldFL: Mitigating Model Poisoning Attacks in Privacy-Preserving Federated LearningIEEE Transactions on Information Forensics and Security, 2022
- Privacy-Enhanced Federated Learning Against Poisoning AdversariesIEEE Transactions on Information Forensics and Security, 2021
- Data Poisoning Attacks Against Federated Learning Systems2020
- Federated Learning With Differential Privacy: Algorithms and Performance AnalysisIEEE Transactions on Information Forensics and Security, 2020
- Deep Residual Learning for Image Recognition2016