A dynamic intrusion detection system for critical information infrastructure

Adejimi, A O; Sodiya, Adesina S.; Ojesanmi, O. A.; Falana, Olorunjube James; Tinubu, C.O.

doi:10.1016/j.sciaf.2023.e01817

Cited by 3 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Due to the necessity and requirements of securing medical data transfer these days, IoMT system infrastructures are required to be designed to be effective in safeguarding the integrity of the collected sensitive and confidential data of healthcare workers and patients. The functionality of an IDS tool is to provide preemptive mitigation for detecting and preventing cyberattacks by identifying the risks and threats that could disrupt and compromise the IoMT’s functionality and performance [ 39 ]. An IDS is an essential requirement in any IoT-based system built and designed for monitoring the network traffic between connected devices to detect irregular activities and classify them as anomalies inside the network.…”

Section: Ids Architecturementioning

confidence: 99%

Security Analysis for Smart Healthcare Systems

Ibrahim,

Al-Wadi,

Elhafiz

2024

Sensors

View full text Add to dashboard Cite

The healthcare industry went through reformation by integrating the Internet of Medical Things (IoMT) to enable data harnessing by transmission mediums from different devices, about patients to healthcare staff devices, for further analysis through cloud-based servers for proper diagnosis of patients, yielding efficient and accurate results. However, IoMT technology is accompanied by a set of drawbacks in terms of security risks and vulnerabilities, such as violating and exposing patients’ sensitive and confidential data. Further, the network traffic data is prone to interception attacks caused by a wireless type of communication and alteration of data, which could cause unwanted outcomes. The advocated scheme provides insight into a robust Intrusion Detection System (IDS) for IoMT networks. It leverages a honeypot to divert attackers away from critical systems, reducing the attack surface. Additionally, the IDS employs an ensemble method combining Logistic Regression and K-Nearest Neighbor algorithms. This approach harnesses the strengths of both algorithms to improve attack detection accuracy and robustness. This work analyzes the impact, performance, accuracy, and precision outcomes of the used model on two IoMT-related datasets which contain multiple attack types such as Man-In-The-Middle (MITM), Data Injection, and Distributed Denial of Services (DDOS). The yielded results showed that the proposed ensemble method was effective in detecting intrusion attempts and classifying them as attacks or normal network traffic, with a high accuracy of 92.5% for the first dataset and 99.54% for the second dataset and a precision of 96.74% for the first dataset and 99.228% for the second dataset.

show abstract

Section: Ids Architecturementioning

confidence: 99%

Security Analysis for Smart Healthcare Systems

Ibrahim,

Al-Wadi,

Elhafiz

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Validasi Model: Memvalidasi model machine learning untuk mengukur kinerjanya. Ini dilakukan dengan membagi data menjadi subset pelatihan dan validasi (atau menggunakan teknik seperti crossvalidation) (Adejimi, 2023). Model akan dinilai berdasarkan metrik seperti akurasi, presisi, recall, F1-score, dan area di bawah kurva ROC (AUC-ROC) (Srinivasan, 2022).…”

Section: Preprocessing Data: Melakukan Preprocessing Dataunclassified

Deteksi Intrusi Siber pada Sistem Pembelajaran Elektronik berbasis Machine Learning

Amirah,

Sanmorino

2023

J. Ilm. Inform. Glob.

View full text Add to dashboard Cite

This study aims to develop a mechanism for detecting machine learning-based cyber intrusions in electronic learning systems. In today's digital era, e-learning systems have become an integral part of education and training, providing global accessibility and more interactive learning efficiency. However, security and privacy challenges are becoming critical issues due to the increasingly real threat of cyber intrusion. Attackers try to take advantage of vulnerabilities and weaknesses in e-learning systems to steal sensitive data or disrupt operations. To overcome this problem, this study focuses on the use of artificial intelligence technologies, especially machine learning, to proactively detect and respond to intrusive threats. Through e-learning security analysis, identification of weaknesses, and potential loopholes for cyber-attacks, the most suitable machine learning algorithms are selected to detect patterns and signs of intrusion attacks on network data. The evaluation results show that several machine learning algorithms, such as SVM and Decision Tree, have good performance in recognizing cyber intrusions with high accuracy, precision, recall, F1-score, and ROC-AUC. By implementing machine learning-based intrusion detection technology, it is expected that electronic learning systems can be more proactive in identifying and responding to intrusion threats before significant damage occurs. This research has significant benefits in increasing security and privacy in the use of electronic learning systems. In addition, this study is expected to be a reference for further research in the world of cyber security and the application of artificial intelligence technology in supporting digital security.

show abstract