Federated Learning-Enhanced Blockchain Framework for Privacy-Preserving Intrusion Detection in Industrial IoT

TL;DR

The paper tackles the challenge of intrusion detection in IIoT under privacy and latency constraints by proposing FL-BCID, a framework that tightly combines federated learning with a permissioned blockchain. Edge devices collaboratively train a lightweight IDS model using federated averaging while sensitive data remains on-device, and a smart-contract-enabled blockchain ensures integrity, audibility, and tamper-resistance of model updates and anomaly scores. The approach achieves high detection accuracy (up to 97.3% on ToN-IoT) and reduces communication overhead by about 41% compared with centralized methods, demonstrating improved privacy, scalability, and robustness for secure industrial operations. The work suggests future directions including adaptive optimization for heterogeneous devices, more efficient consensus mechanisms, and resilience to model poisoning via reputation-based aggregation, positioning FL-BCID as a foundation for secure IIoT deployments.

Abstract

Industrial Internet of Things (IIoT) systems have become integral to smart manufacturing, yet their growing connectivity has also exposed them to significant cybersecurity threats. Traditional intrusion detection systems (IDS) often rely on centralized architectures that raise concerns over data privacy, latency, and single points of failure. In this work, we propose a novel Federated Learning-Enhanced Blockchain Framework (FL-BCID) for privacy-preserving intrusion detection tailored for IIoT environments. Our architecture combines federated learning (FL) to ensure decentralized model training with blockchain technology to guarantee data integrity, trust, and tamper resistance across IIoT nodes. We design a lightweight intrusion detection model collaboratively trained using FL across edge devices without exposing sensitive data. A smart contract-enabled blockchain system records model updates and anomaly scores to establish accountability. Experimental evaluations using the ToN-IoT and N-BaIoT datasets demonstrate the superior performance of our framework, achieving 97.3% accuracy while reducing communication overhead by 41% compared to baseline centralized methods. Our approach ensures privacy, scalability, and robustness-critical for secure industrial operations. The proposed FL-BCID system provides a promising solution for enhancing trust and privacy in modern IIoT security architectures.

Figures (4)

• Figure 1: Model accuracy over federated rounds on IIoT datasets.
• Figure 2: Communication overhead comparison.
• Figure 3: Confusion matrix for FL-BCID on test data.
• Figure 4: Comparison of time to convergence.