Deep Learning Based Attack Detection for Cyber-Physical System Cybersecurity: A Survey

TLDR

Cyber‑physical systems face increasing cyber‑attack threats, and while detection is difficult, deep learning offers superior performance and has rapidly been adopted to address these challenges. This survey provides a holistic view of recent deep‑learning solutions for cyber‑attack detection in CPS. The authors present a six‑step DL‑driven methodology—scenario analysis, attack identification, ML problem formulation, DL model customization, data acquisition, and performance evaluation—to summarize and analyze the literature. The reviewed studies demonstrate that DL modules can effectively detect CPS attacks, achieving excellent performance thanks to high‑quality public datasets, and highlight challenges, opportunities, and future research directions.

Abstract

With the booming of cyber attacks and cyber criminals against cyber-physical systems (CPSs), detecting these attacks remains challenging. It might be the worst of times, but it might be the best of times because of opportunities brought by machine learning (ML), in particular deep learning (DL). In general, DL delivers superior performance to ML because of its layered setting and its effective algorithm for extract useful information from training data. DL models are adopted quickly to cyber attacks against CPS systems. In this survey, a holistic view of recently proposed DL solutions is provided to cyber attack detection in the CPS context. A six-step DL driven methodology is provided to summarize and analyze the surveyed literature for applying DL methods to detect cyber attacks against CPS systems. The methodology includes CPS scenario analysis, cyber attack identification, ML problem formulation, DL model customization, data acquisition for training, and performance evaluation. The reviewed works indicate great potential to detect cyber attacks against CPS through DL modules. Moreover, excellent performance is achieved partly because of several high-quality datasets that are readily available for public use. Furthermore, challenges, opportunities, and research trends are pointed out for future research.