Abnormal Client Behavior Detection in Federated Learning

Abstract

In federated learning systems, clients are autonomous in that their behaviors are not fully governed by the server. Consequently, a client may intentionally or unintentionally deviate from the prescribed course of federated model training, resulting in abnormal behaviors, such as turning into a malicious attacker or a malfunctioning client. Timely detecting those anomalous clients is therefore critical to minimize their adverse impacts. In this work, we propose to detect anomalous clients at the server side. In particular, we generate low-dimensional surrogates of model weight vectors and use them to perform anomaly detection. We evaluate our solution through experiments on image classification model training over the FEMNIST dataset. Experimental results show that the proposed detection-based approach significantly outperforms the conventional defense-based methods.

7 pages, 1 figure, 2nd International Workshop on Federated Learning for Data Privacy and Confidentiality, in Conjunction with NeurIPS 2019 (FL-NeurIPS 19)

References in corpus (15)

• Deep Learning with Differential Privacy
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Federated Learning: Strategies for Improving Communication Efficiency
• Towards Federated Learning at Scale: System Design
• How To Backdoor Federated Learning
• Federated Machine Learning: Concept and Applications
• Differentially Private Federated Learning: A Client Level Perspective
• Federated Optimization in Heterogeneous Networks
• Linear Dimensionality Reduction: Survey, Insights, and Generalizations
• LEAF: A Benchmark for Federated Settings
• Practical Secure Aggregation for Federated Learning on User-Held Data
• Privacy-Preserving Deep Learning via Weight Transmission
• Federated Multi-Task Learning
• Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach
• Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms

Cited by in corpus (15)

• From Distributed Machine Learning to Federated Learning: A Survey
• Block Hunter: Federated Learning for Cyber Threat Hunting in Blockchain-based IIoT Networks
• DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspection
• Edge Intelligence: Architectures, Challenges, and Applications
• Towards Communication-efficient and Attack-Resistant Federated Edge Learning for Industrial Internet of Things
• Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategies
• Federated Continual Learning: Concepts, Challenges, and Solutions
• FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusion
• An On-Device Federated Learning Approach for Cooperative Model Update between Edge Devices
• Byzantines can also Learn from History: Fall of Centered Clipping in Federated Learning
• PIRATE: A Blockchain-based Secure Framework of Distributed Machine Learning in 5G Networks
• Federated Learning -- Methods, Applications and beyond
• DistFL: Distribution-aware Federated Learning for Mobile Scenarios
• Towards On-Device Federated Learning: A Direct Acyclic Graph-based Blockchain Approach
• Sample Selection Using Multi-Task Autoencoders in Federated Learning with Non-IID Data