"CPS Multimodal Network Security Dataset"

Abstract

"This dataset provides network traffic and physical sensor measurements intended to support research on cybersecurity, anomaly detection, machine learning, and multimodal security analysis in Cyber-Physical Systems (CPS). The network component contains 528,856 observations characterized by flow identifiers, source and destination information, protocol attributes, packet statistics, traffic-direction information, and attack labels. The sensor component contains 4,100 observations comprising temperature, humidity, atmospheric pressure, CO\u2082 concentration, PM2.5, PM10, temporal information, and daytime classification. The dataset can support experiments involving network intrusion detection, attack classification, anomaly detection, feature-selection techniques, machine-learning models, and federated-learning-based CPS security. Documentation describing the attributes, data types, class distributions, preprocessing considerations, and intended research applications is supplied with the dataset to facilitate reproducibility and reuse."