Security and Privacy Issues and Solutions in Federated Learning for Digital Healthcare
It tackles critical security and privacy challenges for healthcare applications using federated learning, but the work appears incremental as it builds on existing knowledge without presenting new experimental results or specific performance gains.
The paper addresses security and privacy vulnerabilities in federated learning for digital healthcare, identifying attacks and defenses based on widened attack surfaces and proposing research directions for more robust systems.
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.