TemporalFED: Detecting Cyberattacks in Industrial Time-Series Data Using Decentralized Federated Learning

Industry 4.0 has brought numerous advantages, such as increasing productivity through automation. However, it also presents major cybersecurity issues, such as cyberattacks affecting industrial processes. Federated Learning (FL) combined with time-series analysis is a promising cyberattack detection mechanism proposed in the literature. However, having a single point of failure and network bottleneck are critical challenges that need to be tackled. Thus, this article explores the benefits of the Decentralized Federated Learning (DFL) in terms of cyberattack detection and resource consumption. The work presents TemporalFED, a software module for detecting cyberattacks in industrial environments using FL paradigms and time series. TemporalFED incorporates three components: time series conversion, feature engineering, and stationary conversion. To evaluate TemporalFED, itwas deployed on Fedstellar, a DFL framework. Then, a pool of experiments measured the detection performance and resource consumption in a chemical gas industrial environment with different time-series configurations, FL paradigms, and topologies. The results showcase the superiority of the configuration utilizing DFL and Semi-Decentralized Federated Learning (SDFL) paradigms, along with a fully connected topology, which achieved the best performance in anomaly detection. Regarding resource consumption, the configuration without feature engineering employed less bandwidth, less usage of the Central Processing Unit (CPU), and less usage of the Random Access Memory (RAM) than other configurations.