Machine Learning Methods for Industrial Protocol Security Analysis: Issues, Taxonomy, and Directions

Men, Jiaping; Lv, Zhuo; Zhou, Xiaojun; Han, Zhen; Xian, Hequn; Song, Yanan

doi:10.1109/access.2020.2976745

Cited by 11 publications

(6 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A survey on machine learning methods for the security of industrial protocols is presented in [77]. Since the main focus of the article [77] is on the protocols, the security weaknesses in many protocols are exposed.…”

Section: Our Articlementioning

confidence: 99%

Communications Security in Industry X: A Survey

Ahmad,

Rodriguez,

Kumar

et al. 2024

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

Industry 4.0 is moving towards deployment using 5G as one of the main underlying communication infrastructures. Thus, the vision of the Industry of the future is getting more attention in research. Industry X (InX) is a significant thrust beyond the state-of-the-art of current Industry 4.0, towards a mix of cyber and physical systems through novel technological developments. In this survey, we define InX as the combination of Industry 4.0 and 5.0 paradigms. Most of the novel technologies, such as cyber-physical systems, industrial internet of things, machine learning, advances in cloud computing, such as edge and fog computing, and blockchain, to name a few, are converged through advanced communication networks. Since communication networks are usually targeted for security attacks, these new technologies upon which InX relies must be secured to avoid security vulnerabilities propagating into InX and its components. Therefore, in this article, we break down the security concerns of the converged InXcommunication networks into the core technologies that tie these, once considered distinct, fields together. The security challenges of each technology are highlighted and potential solutions are discussed. The existing vulnerabilities or research gaps are brought forth to stir further research in this direction. New emerging visions in the context of InX are provided towards the end of the article to provoke further curiosity of researchers.

show abstract

Section: Our Articlementioning

confidence: 99%

Communications Security in Industry X: A Survey

Ahmad,

Rodriguez,

Kumar

et al. 2024

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

show abstract

Section: Our Article Communications Security In Inxmentioning

confidence: 99%

“…A survey on machine learning methods for the security of industrial protocols is presented in [73]. Since the main focus of the article [73] is on the protocols, the security weaknesses in many protocols are exposed. The authors provide methods of machine learning that are most helpful in analyzing the security of protocols in ICS.…”

Section: Our Article Communications Security In Inxmentioning

confidence: 99%

Communications Security in Industry X: A Survey

Ahmad¹,

Rodríguez²,

Kumar³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…However, at present, research efforts are typically focusing on developing new techniques using innovative technologies such as Big Data [20] or ML/DL. In particular, the use of ML and DL techniques is increasing, which play a key role in detecting cyber attacks affecting the industrial field [21]. This section performs an exhaustive review of the most relevant works related to ML/DL for anomaly detection in the industrial context.…”

Section: Related Workmentioning

confidence: 99%

MADICS: A Methodology for Anomaly Detection in Industrial Control Systems

et al. 2020

View full text Add to dashboard Cite

Industrial Control Systems (ICSs) are widely used in critical infrastructures to support the essential services of society. Therefore, their protection against terrorist activities, natural disasters, and cyber threats is critical. Diverse cyber attack detection systems have been proposed over the years, in which each proposal has applied different steps and methods. However, there is a significant gap in the literature regarding methodologies to detect cyber attacks in ICS scenarios. The lack of such methodologies prevents researchers from being able to accurately compare proposals and results. In this work, we present a Methodology for Anomaly Detection in Industrial Control Systems (MADICS) to detect cyber attacks in ICS scenarios, which is intended to provide a guideline for future works in the field. MADICS is based on a semi-supervised anomaly detection paradigm and makes use of deep learning algorithms to model ICS behaviors. It consists of five main steps, focused on pre-processing the dataset to be used with the machine learning and deep learning algorithms; performing feature filtering to remove those features that do not meet the requirements; feature extraction processes to obtain higher order features; selecting, fine-tuning, and training the most appropriate model; and validating the model performance. In order to validate MADICS, we used the popular Secure Water Treatment (SWaT) dataset, which was collected from a fully operational water treatment plant. The experiments demonstrate that, using MADICS, we can achieve a state-of-the-art precision of 0.984 (as well as a recall of 0.750 and F1-score of 0.851), which is above the average of other works, proving that the proposed methodology is suitable for use in real ICS scenarios.

show abstract

Machine Learning Methods for Industrial Protocol Security Analysis: Issues, Taxonomy, and Directions

Cited by 11 publications

References 77 publications

Communications Security in Industry X: A Survey

Communications Security in Industry X: A Survey

Communications Security in Industry X: A Survey

MADICS: A Methodology for Anomaly Detection in Industrial Control Systems

Contact Info

Product

Resources

About