Protecting Water Infrastructure From Cyber and Physical Threats: Using Multimodal Data Fusion and Adaptive Deep Learning to Monitor Critical Systems

Abstract

Critical water infrastructure is susceptible to various types of major attacks, including direct, human-presence assaults and cyberattacks tampering with industrial control system (ICS) sensors and processes. As attacks become increasingly sophisticated and multifaceted, their timely detection becomes especially challenging and requires the exploitation of different data modalities, such as visual surveillance, channel state information (CSI) from Wi-Fi signals for human-presence detection, and ICS sensor data from the utility.