期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2021
卷号：12
期号：5
页码：37
DOI：10.14569/IJACSA.2021.0120506
出版社：Science and Information Society (SAI)
摘要：Cyber-physical systems (CPS) integrate computa-tion and communication capabilities to monitor and control physical systems. Even though this integration improves the performance of the overall system and facilitates the application of CPS in several domains, it also introduces security challenges. Over the years, intrusion detection systems (IDS) have been de-ployed as one of the security controls for addressing these security challenges. Traditionally, there are three main approaches to IDS, namely: anomaly detection, misuse detection and specification-based detection. However, due to the unique attributes of CPS, the traditional IDS need to be modified or completely replaced before it can be deployed for CPS. In this paper, we present a survey of specification-based intrusion detection techniques for CPS. We classify the existing specification-based intrusion detection techniques in the literature according to the following attributes: specification source, specification extraction, specifi-cation modelling, detection mechanism, detector placement and validation strategy. We also discuss the details of each attribute and describe our observations, concerns and future research directions. We argue that reducing the efforts and time needed to extract the system specification of specification-based intrusion detection techniques for CPS and verifying the correctness of the extracted system specification are open issues that must be addressed in the future.
