BlockFedIDS: A Blockchain-Enabled Federated Learning Framework for Privacy-Preserving Intrusion Detection in Heterogeneous IoT Networks

Abstract

The rapid growth of IoT networks demands privacy-preserving intrusion detection systems that operate on distributed data without exposing sensitive traffic information. This paper presents BlockFedIDS, a blockchain-enabled federated learning framework that eliminates the centralised aggregator using smart contracts. The framework integrates Differentially Private Stochastic Gradient Descent (DP-SGD) for differential privacy, Multi-Krum for Byzantine-resilient aggregation, and Pedersen commitments for secure model update verification. Experimental evaluation on the NSL-KDD and CIC-IDS2017 datasets with 20 IoT clients achieves 97.14% detection accuracy and 0.984 F1-score, while reducing poisoning-induced performance degradation by 74.3% compared with FedAvg and requiring only 1.4 KB of on-chain storage per training round.