Dynamic Defense Against Byzantine Poisoning Attacks in Federated Learning

Abstract

Federated learning, as a distributed learning that conducts the training on the local devices without accessing to the training data, is vulnerable to Byzatine poisoning adversarial attacks. We argue that the federated learning model has to avoid those kind of adversarial attacks through filtering out the adversarial clients by means of the federated aggregation operator. We propose a dynamic federated aggregation operator that dynamically discards those adversarial clients and allows to prevent the corruption of the global learning model. We assess it as a defense against adversarial attacks deploying a deep learning classification model in a federated learning setting on the Fed-EMNIST Digits, Fashion MNIST and CIFAR-10 image datasets. The results show that the dynamic selection of the clients to aggregate enhances the performance of the global learning model and discards the adversarial and poor (with low quality models) clients.

10 pages

References in corpus (6)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Federated Optimization: Distributed Machine Learning for On-Device Intelligence
• Federated Learning and Differential Privacy: Software tools analysis, the Sherpa.ai FL framework and methodological guidelines for preserving data privacy
• Exploring the Limits of Out-of-Distribution Detection
• Free-riders in Federated Learning: Attacks and Defenses
• Privacy and Robustness in Federated Learning: Attacks and Defenses

Cited by in corpus (1)

• RAB${}^2$-DEF: Dynamic and explainable defense against adversarial attacks in Federated Learning to fair poor clients