Adversarial Reinforcement Learning Applications in Cyber-Physical Systems Security
Published in Pennsylvania State University, 2026
Abstract
This doctoral dissertation addresses the evolving challenges in computer and network security, emphasizing a need for a comprehensive framework that integrates proactive prevention, effective detection, and adaptive mitigation strategies across cyber-physical systems. The research introduces scalable multi-agent and deep reinforcement learning algorithms tailored to three key domains: (1) proactive prevention of threats using automated Moving Target Defense (MTD) configurations, (2) robust detection of stealthy False Data Injection (FDI) attacks in crowdsourced transportation networks using Policy Space Response Oracles, and (3) resilient real-time control policies for mitigating cyber-attacks on Industrial Control Systems (ICS).
BibTeX
@phdthesis{eghtesad2026adversarial,
author = {Eghtesad, Taha},
title = {Adversarial Reinforcement Learning Applications in Cyber-Physical Systems Security},
school = {Pennsylvania State University},
year = {2026},
url = {https://etda.libraries.psu.edu/catalog/29643txe5135}
}