Security and Privacy Issues and Solutions in Federated Learning for Digital Healthcare

Abstract

The advent of Federated Learning has enabled the creation of a high-performing model as if it had been trained on a considerable amount of data. A multitude of participants and a server cooperatively train a model without the need for data disclosure or collection. The healthcare industry, where security and privacy are paramount, can substantially benefit from this new learning paradigm, as data collection is no longer feasible due to stringent data policies. Nonetheless, unaddressed challenges and insufficient attack mitigation are hampering its adoption. Attack surfaces differ from traditional centralized learning in that the server and clients communicate between each round of training. In this paper, we thus present vulnerabilities, attacks, and defenses based on the widened attack surfaces, as well as suggest promising new research directions toward a more robust FL.

References in corpus (15)

• Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
• Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge
• How To Backdoor Federated Learning
• FedKD: Communication Efficient Federated Learning via Knowledge Distillation
• Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
• The Hidden Vulnerability of Distributed Learning in Byzantium
• Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data
• Analyzing Federated Learning through an Adversarial Lens
• Can You Really Backdoor Federated Learning?
• Threats to Federated Learning: A Survey
• Attack of the Tails: Yes, You Really Can Backdoor Federated Learning
• Free-riders in Federated Learning: Attacks and Defenses
• Mitigating Backdoor Attacks in Federated Learning
• PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments
• Fairness and Accuracy in Federated Learning