SECURE FEDERATED LEARNING WITH BLOCKCHAIN AND SMPC: PROTECTING HEALTHCARE SYSTEMS FROM POISONING ATTACKS

Abstract

Federated learning (FL) has been used to several domains, such as smart cities, intelligent healthcare systems, and sectors reliant on the internet of things (IoT). This is in response to the growing concern about privacy and security in machine learning applications. Clients may work together to train a global model using FL, even when they don't have access to the same data as before. Nevertheless, adversarial attacks may exploit the weaknesses of existing FL methods. Because of its design, protecting against harmful model changes and identifying them are both made difficult. Not enough has been investigated in the most current research on protecting the model's privacy while detecting FL from harmful updates. This study presented a solution to the problem of poisoning assaults on healthcare systems: federated learning based on blockchain technology with SMPC model verification. We start by removing the compromised model after verifying it via an encrypted inference procedure using the FL participants' machine learning models. After each participant's local model is checked, it is safely forwarded to the blockchain node for aggregation. In order to test our proposed framework, we used a variety of medical datasets in a number of studies.