TrustChain: A Blockchain Framework for Auditing and Verifying Aggregators in Decentralized Federated Learning

--The server-less nature of Decentralized Federated Learning (DFL) requires allocating the aggregation role to specific participants in each federated round. Current DFL architectures ensure the trustworthiness of the aggregator node upon selection. However, most of these studies overlook the possibility that the aggregating node may turn rogue and act maliciously after being nominated. T o address this problem, this paper proposes a DFL structure, called TrustChain, that scores the aggregators before selection based on their past behavior and additionally audits them after the aggregation. T o do this, the statistical independence between the client updates and the aggregated model is continuously monitored using the Hilbert-Schmidt Independence Criterion (HSIC). The proposed method relies on several principles, including blockchain, anomaly detection, and concept drift analysis. The designed structure is evaluated on several federated datasets and attack scenarios with different numbers of Byzantine nodes. HE advent of Federated Learning (FL) advanced the field of distributed machine learning by introducing data decentralization as a solution to bring about data privacy and communication efficiency [1]. Despite its advantages, FL was shown to be vulnerable against a spectrum of adversaries due to its distributed nature [2], [3]. Numerous research endeavors have been dedicated to studying these threats and finding robust defense mechanisms to mitigate them. A common perception among the majority of these studies is that the server is trustworthy, and malicious activities can potentially be initiated from the edge nodes.