Attack-Resistant Federated Learning with Residual-based Reweighting
arXiv:1912.11464
Abstract
Federated learning has a variety of applications in multiple domains by utilizing private training data stored on different devices. However, the aggregation process in federated learning is highly vulnerable to adversarial attacks so that the global model may behave abnormally under attacks. To tackle this challenge, we present a novel aggregation algorithm with residual-based reweighting to defend federated learning. Our aggregation algorithm combines repeated median regression with the reweighting scheme in iteratively reweighted least squares. Our experiments show that our aggregation algorithm outperforms other alternative algorithms in the presence of label-flipping and backdoor attacks. We also provide theoretical analysis for our aggregation algorithm.
arXiv comment8 pages, 6 figures and 4 tables
References in corpus (14)
- Adam: A Method for Stochastic Optimization
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Deep Residual Learning for Image Recognition
- How To Backdoor Federated Learning
- Poisoning Attacks against Support Vector Machines
- Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
- Differentially Private Federated Learning: A Client Level Perspective
- Mitigating Sybils in Federated Learning Poisoning
- Byzantine Stochastic Gradient Descent
- Differentially Private Learning with Adaptive Clipping
- A Hybrid Approach to Privacy-Preserving Federated Learning
- Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning
- Distributed Robust Learning
- Reaching Data Confidentiality and Model Accountability on the CalTrain
Cited by in corpus (9)
- Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges
- Learning from History for Byzantine Robust Optimization
- Securing Federated Sensitive Topic Classification against Poisoning Attacks
- Blockchain-Based Federated Learning in Mobile Edge Networks with Application in Internet of Vehicles
- DistFL: Distribution-aware Federated Learning for Mobile Scenarios
- Robust Federated Learning with Attack-Adaptive Aggregation
- Towards Bidirectional Protection in Federated Learning
- Federated Learning with Unreliable Clients: Performance Analysis and Mechanism Design
- Toward Smart Security Enhancement of Federated Learning Networks