Intelligent Attacks on Cyber-Physical Systems and Critical Infrastructures

TL;DR

The chapter analyzes intelligent cyber-physical attacks on CPSs and critical infrastructures, detailing how AI can enable stealthy, automated, and adaptive threats in both OT and IT settings. It categorizes attacks into Cyber-Physical Intelligence (CPI) and Model-based families, outlining passive and active system identification (PSI/ASI) and subsequent data injection, jitter, and data loss through SD-CDI, SD-CDI with covert misappropriation, and SD-CDL. Concrete pathways are provided, including Modbus/PROFINET-based scenarios and the use of MitM to implement covert disruptions after learning plant and controller models. The discussion proposes defenses that hinder attacker learning, enforce network segmentation, and improve real-time adaptability, while highlighting open research directions for robust CPS security and dual-use risk management.

Abstract

This chapter provides an overview of the evolving landscape of attacks in cyber-physical systems (CPS) and critical infrastructures, highlighting the possible use of Artificial Intelligence (AI) algorithms to develop intelligent cyberattacks. It describes various existing methods used to carry out intelligent attacks in Operational Technology (OT) environments and discusses AI-driven tools that automate penetration tests in Information Technology (IT) systems, which could potentially be used as attack tools. The chapter also discusses mitigation strategies to counter these emerging intelligent attacks by hindering the learning process of AI-based attacks and points to future research directions on the matter.

Figures (7)

• Figure 1: Evolution and trends of cyberattacks. (Adapted from di2018triton)
• Figure 2: Roadmap for intelligent cyberattacks.
• Figure 3: Passive System Identification attack.
• Figure 4: Active System Identification attack.
• Figure 5: SD-CDI attack.