Federated Learning in Adversarial Settings
Federated Learning enables entities to collaboratively learn a shared prediction model while keeping their training data locally. It prevents data collection and aggregation and, therefore, mitigates the associated privacy risks. However, it still remains vulnerable to various security attacks where malicious participants aim at degrading the generated model, inserting backdoors, or inferring other participants' training data. This paper presents a new federated learning scheme that provides different trade-offs between robustness, privacy, bandwidth efficiency, and model accuracy. Our scheme uses biased quantization of model updates and hence is bandwidth efficient. It is also robust against state-of-the-art backdoor as well as model degradation attacks even when a large proportion of the participant nodes are malicious. We propose a practical differentially private extension of this scheme which protects the whole dataset of participating entities. We show that this extension performs as efficiently as the non-private but robust scheme, even with stringent privacy requirements but are less robust against model degradation and backdoor attacks. This suggests a possible fundamental trade-off between Differential Privacy and robustness.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningQuantizationSimilar Papers 제목 키워드 기반
Delving into the Adversarial Robustness of Federated Learning
In Federated Learning (FL), models are as fragile as centrally trained models against adversarial examples. However, the adversarial robustness of federated learning remains largely unexplored. This paper casts light on …
Adversarial RobustnessFederated LearningFAT: Federated Adversarial Training
Federated learning (FL) is one of the most important paradigms addressing privacy and data governance issues in machine learning (ML). Adversarial training has emerged, so far, as the most promising approach against evas…
Adversarial RobustnessFederated LearningEnsemble Federated Adversarial Training with Non-IID data
Despite federated learning endows distributed clients with a cooperative training mode under the premise of protecting data privacy and security, the clients are still vulnerable when encountering adversarial samples due…
DiversityFederated LearningFed-Safe: Securing Federated Learning in Healthcare Against Adversarial Attacks
This paper explores the security aspects of federated learning applications in medical image analysis. Current robustness-oriented methods like adversarial training, secure aggregation, and homomorphic encryption often r…
Federated LearningMedical Image AnalysisThe Hidden Adversarial Vulnerabilities of Medical Federated Learning
In this paper, we delve into the susceptibility of federated medical image analysis systems to adversarial attacks. Our analysis uncovers a novel exploitation avenue: using gradient information from prior global model up…
Federated LearningMedical Image Analysis