An Efficient Intrusion Detection Framework for Industrial Internet of Things Security

Alshathri, Samah; El‐Sayed, Ayman; El‐Shafai, Walid; Hemdan, Ezz El‐Din

doi:10.32604/csse.2023.034095

Cited by 10 publications

(8 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed IDS framework 38 offers protection against malicious activities in IoT infrastructure. ML algorithms were used for intrusion detection: Logistic regression, Linear discriminant analysis, K-nearest neighbours, Gaussian naive Bayes, Classification and regression tree, Random forest, and AdaBoost.…”

Section: Resultsmentioning

confidence: 99%

Internet of Medical Things Security Frameworks for Risk Assessment and Management: A Scoping Review

Svandova,

Smutny

2024

JMDH

View full text Add to dashboard Cite

Background The massive expansion of the Internet of medical things (IoMT) technology brings many opportunities for improving healthcare. At the same time, their use increases security risks, brings security and privacy concerns, and threatens the functioning of healthcare facilities or healthcare provision. Purpose This scoping review aims to identify progress in designing risk assessment and management frameworks for IoMT security. The frameworks found are divided into two groups according to whether frameworks address the technological design of risk management or assess technological measures to ensure the security of the IoMT environment. Furthermore, the article intends to find out whether frameworks also include an assessment of organisational measures related to IoMT security. Methods This review was prepared using PRISMA ScR guidelines. Relevant studies were searched in the citation databases Web of Science and Scopus. The search was limited to articles published in English between 2018 and 17 September 2023. The initial search yielded 1341 articles, of which 44 (3.3%) were included in the scoping review. A qualitative content analysis focused on selected security perspectives and progress in the given area was carried out. Results Thirty-two articles describe the design of risk assessment and management frameworks. Twelve articles describe the design of frameworks for assessing the security of IoMT devices and possibly offer a comparison of different IoMT alternatives. A description of the included articles was prepared from the selected security perspectives. Conclusion The review shows the need to create comprehensive or holistic frameworks for operational security and privacy risk management at all layers of the IoMT architecture. It includes the design of specific technological solutions and frameworks for continuously assessing the overall level of information security and privacy of the IoMT environment. Unfortunately, none of the found frameworks offer an assessment of organizational measures even though the importance of the organization measures was highlighted in articles. Another area of interest for researchers could be the design of a general risk management database for IoMT, which would include potential IoMT-related risks connected to a particular device.

show abstract

Section: Resultsmentioning

confidence: 99%

Internet of Medical Things Security Frameworks for Risk Assessment and Management: A Scoping Review

Svandova,

Smutny

2024

JMDH

View full text Add to dashboard Cite

show abstract

“…Among them, L represents the loss value obtained based on the true and predicted values when establishing the t-th tree, and Ω represents its corresponding regularization term. Select the regularization term given in formula (7) based on LightGBM:…”

Section: Lightgbm Feature Algorithm Theorymentioning

confidence: 99%

“…Intrusion security detection technology is a commonly used technology that can greatly ensure the security and integrity of industrial IoT system data. Combined with the IoT network intrusion security detection mechanism, it generates alarm data and quickly presents data behaviour to security technicians to avoid damage and loss [6,7].…”

Section: Introductionmentioning

confidence: 99%

Design of Industrial IoT Intrusion Security Detection System Based on LightGBM Feature Algorithm and Multi-layer Perception Network

Deng

2024

JCSANDM

View full text Add to dashboard Cite

Continuous improvement of machine learning technology has provided more support for intrusion security detection in the industrial Internet of Things (IoT). The intrusion security detection system based on LightGBM feature algorithm and multi-layer perception network fusion provides more options for improving security detection, further enhancing the effectiveness of industrial IoT intrusion security detection. By comparing the applications of different models in the security detection process, the model constructed based on the LightGBM feature algorithm can achieve higher accuracy and precision in industrial IoT intrusion security detection, as well as higher F1-score and AUC values; A more reasonable detection time also lays the foundation for improving the overall efficiency of industrial IoT intrusion security detection. Therefore, in the field of industrial IoT intrusion security detection, the detection model constructed in this article can provide more support for further improvement and improvement of IoT intrusion security detection performance.

show abstract

“…A DT [38] is one of the most efficient ML algorithms. It uses a tree structure with N nodes that contain conditions for classifying data points according to their features.…”

Section: Machine Learning Algorithmsmentioning

confidence: 99%

The development of a model for the threat detection system with the use of machine learning and neural network methods

Ussatova,

Zhumabekova,

Karyukin

et al. 2024

ijirss

View full text Add to dashboard Cite

This study examines the development of a model for the threat detection system with the use of machine learning and neural network methods. The fast development of Internet technologies has led to the appearance of many digital systems and platforms. However, despite the impressive technological progress, another side also emerged in the spread of a massive number of different cyber threats. Although various ways have been created to detect and prevent them, the threats are also developing and becoming more complex each year. Therefore, new system defense and data protection methods using machine and deep learning approaches have been proposed recently. The methods based on these approaches have proved to be especially effective in the wave of new Artificial Intelligence applications. In this paper, a threat detection system has been designed to disclose different kinds of threats while maintaining the security, confidentiality, and availability of the computer system. The development of machine learning models for detecting DDoS and man-in-the-middle attacks, Structured Query Language (SQL) injections, phishing, and malware was examined. The data scaling, feature selection, feature extraction, and classification steps were also thoroughly described. Naïve Bayes, Logistic Regression, Decision Tree, Random Forest, XGBoost, CatBoost, and Deep Neural Network algorithms were utilized for training the cyber threat detection models. The experimental results evaluated all the models using accuracy, precision, recall, and F1-score metrics. The best models achieved scores in the range of 0.90 to 1.00.

show abstract

An Efficient Intrusion Detection Framework for Industrial Internet of Things Security

Cited by 10 publications

References 31 publications

Internet of Medical Things Security Frameworks for Risk Assessment and Management: A Scoping Review

Internet of Medical Things Security Frameworks for Risk Assessment and Management: A Scoping Review

Design of Industrial IoT Intrusion Security Detection System Based on LightGBM Feature Algorithm and Multi-layer Perception Network

The development of a model for the threat detection system with the use of machine learning and neural network methods

Contact Info

Product

Resources

About