Learning to Detect Malicious Clients for Robust Federated Learning

Abstract

Federated learning systems are vulnerable to attacks from malicious clients. As the central server in the system cannot govern the behaviors of the clients, a rogue client may initiate an attack by sending malicious model updates to the server, so as to degrade the learning performance or enforce targeted model poisoning attacks (a.k.a. backdoor attacks). Therefore, timely detecting these malicious model updates and the underlying attackers becomes critically important. In this work, we propose a new framework for robust federated learning where the central server learns to detect and remove the malicious model updates using a powerful detection model, leading to targeted defense. We evaluate our solution in both image classification and sentiment analysis tasks with a variety of machine learning models. Experimental results show that our solution ensures robust federated learning that is resilient to both the Byzantine attacks and the targeted model poisoning attacks.

7 pages, 5 figures

References in corpus (11)

• Communication-Efficient Learning of Deep Networks from Decentralized Data
• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
• On the Convergence of FedAvg on Non-IID Data
• How To Backdoor Federated Learning
• FedMD: Heterogenous Federated Learning via Model Distillation
• Federated Optimization in Heterogeneous Networks
• Can You Really Backdoor Federated Learning?
• Local Model Poisoning Attacks to Byzantine-Robust Federated Learning
• Generalized Byzantine-tolerant SGD
• Dive into Deep Learning
• Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach

Cited by in corpus (20)

• Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges
• DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspection
• A Decentralized Federated Learning Framework via Committee Mechanism with Convergence Guarantee
• An Overview of Federated Learning at the Edge and Distributed Ledger Technologies for Robotic and Autonomous Systems
• Mitigating Backdoor Attacks in Federated Learning
• Auto-weighted Robust Federated Learning with Corrupted Data Sources
• FLrce: Resource-Efficient Federated Learning with Early-Stopping Strategy
• Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective
• Robust Federated Recommendation System
• FedCCEA : A Practical Approach of Client Contribution Evaluation for Federated Learning
• Hijack Vertical Federated Learning Models As One Party
• Byzantine-Robust Variance-Reduced Federated Learning over Distributed Non-i.i.d. Data
• FedSV: Byzantine-Robust Federated Learning via Shapley Value
• An Exploratory Analysis on Users' Contributions in Federated Learning
• Sample Selection Using Multi-Task Autoencoders in Federated Learning with Non-IID Data
• Robust Federated Learning with Attack-Adaptive Aggregation
• ABC-FL: Anomalous and Benign client Classification in Federated Learning
• MANDERA: Malicious Node Detection in Federated Learning via Ranking
• Bristle: Decentralized Federated Learning in Byzantine, Non-i.i.d. Environments
• Toward Smart Security Enhancement of Federated Learning Networks