Robust Federated Learning under Adversarial Attacks via Loss-Based Client Clustering
Federated Learning (FL) enables collaborative model training across multiple clients without sharing private data. We consider FL scenarios wherein FL clients are subject to adversarial (Byzantine) attacks, while the FL server is trusted (honest) and has a trustworthy side dataset. This may correspond to, e.g., cases where the server possesses trusted data prior to federation, or to the presence of a trusted client that temporarily assumes the server role. Our approach requires only two honest participants, i.e., the server and one client, to function effectively, without prior knowledge of the number of malicious clients. Theoretical analysis demonstrates bounded optimality gaps even under strong Byzantine attacks. Experimental results show that our algorithm significantly outperforms standard and robust FL baselines such as Mean, Trimmed Mean, Median, Krum, and Multi-Krum under various attack strategies including label flipping, sign flipping, and Gaussian noise addition across MNIST, FMNIST, and CIFAR-10 benchmarks using the Flower framework.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
FedGreed: A Byzantine-Robust Loss-Based Aggregation Method for Federated Learning
Federated Learning (FL) enables collaborative model training across multiple clients while preserving data privacy by keeping local datasets on-device. In this work, we address FL settings where clients may behave advers…
Federated LearningCharacterizing Internal Evasion Attacks in Federated Learning
Federated learning allows for clients in a distributed system to jointly train a machine learning model. However, clients' models are vulnerable to attacks during the training and testing phases. In this paper, we addres…
Adversarial RobustnessFederated LearningPersonalized Federated LearningRecommendation SystemsDynamic Defense Against Byzantine Poisoning Attacks in Federated Learning
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 l…
Data PoisoningFederated LearningImage ClassificationA Huber Loss Minimization Approach to Byzantine Robust Federated Learning
Federated learning systems are susceptible to adversarial attacks. To combat this, we introduce a novel aggregator based on Huber loss minimization, and provide a comprehensive theoretical analysis. Under independent and…
Federated LearningAn Empirical Analysis of Federated Learning Models Subject to Label-Flipping Adversarial Attack
In this paper, we empirically analyze adversarial attacks on selected federated learning models. The specific learning models considered are Multinominal Logistic Regression (MLR), Support Vector Classifier (SVC), Multil…
Adversarial AttackFederated Learning