Towards Securing IIoT: An Innovative Privacy-Preserving Anomaly Detector Based on Federated Learning

2026-04-07

AI Summary

This study addresses the escalating risks of cyberattacks and data breaches in Industrial Internet of Things (IIoT) environments by proposing a privacy-preserving anomaly detection framework that integrates federated learning with homomorphic encryption. The approach trains models locally to eliminate the need for sharing raw data, thereby enhancing data confidentiality. It further introduces an innovative dynamic proxy selection mechanism based on latency and data volume, which effectively mitigates communication bottlenecks and straggler effects in heterogeneous IIoT settings. Experimental results demonstrate that the proposed framework significantly outperforms existing baseline methods across multiple performance metrics, including accuracy, precision, F1-score, convergence speed, communication overhead, and fairness.

Abstract

In the light of the growing connectivity and sensitivity of industrial data, cyberattacks and data breaches are becoming more common in the Industrial Internet of Things (IIoT). To cope with such threats, this study presents an anomaly detection system based on a novel Federated Learning (FL) framework. This system detects anomalies such as cyberattacks and protects industrial data privacy by processing data locally and training anomaly detection models on industrial agents without sharing raw data. The proposed FL framework incorporates two key components to enhance both privacy and efficiency. The first component is Homomorphic Encryption (HE), which is integrated into the framework to further protect sensitive data transmissions such as model parameters. HE enhances privacy in FL by preventing adversaries from inferring private industrial data through attacks, such as model inversion attacks. The second component is an innovative dynamic agent selection scheme, wherein a selection threshold is calculated based on agent delays and data size. The purpose of this new scheme is to mitigate the straggler effect and the communication bottleneck that occur in traditional FL architectures, such as synchronous and asynchronous architectures. It ensures that agents are not unfairly selected by the different delays resulting from heterogeneous data in IIoT environments, while simultaneously improving model performance and convergence speed. The proposed framework exhibits superior performance over baseline approaches in terms of accuracy, precision, F1-scores, communication costs, convergence speeds, and fairness rate.

Problem

• Industrial Internet of Things
• anomaly detection
• privacy preservation
• cyberattacks
• data breaches

Innovation

• Federated Learning
• Homomorphic Encryption
• Dynamic Agent Selection
• Privacy-Preserving Anomaly Detection
• Industrial Internet of Things