Optimal network intrusion detection assignment in multi-level IoT systems

Dao, Thi-Nga; Le, Duc Van; Tran, Xuan Nam

doi:10.1016/j.comnet.2023.109846

Cited by 4 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intrusion detection is a technology that timely detects and reports unauthorized access or anomalies. Network intrusion detection systems are important network defense tools used to protect systems from illegal attacks, which can improve system reliability and security by detecting and responding to various malicious behaviors [1][2][3][4][5].…”

Section: Introductionmentioning

confidence: 99%

Network intrusion detection utilizing information entropy measurement-based LLE and weighted kernel extreme learning machine with CPSO

Yao,

Chen,

Zhang

2023

Preprint

View full text Add to dashboard Cite

In this study, network intrusion detection method of information entropy measurement-based LLE and weighted kernel extreme learning machine with CPSO (IEMLLE-CWKELM) is proposed for network intrusion detection. First of all, this article proposes an information entropy measurement-based locally linear embedding (IEMLLE) algorithm to reduce the features of network intrusion data. The IEMLLE algorithm is a dimensionality reduction algorithm based on information entropy measurement. The discrimination of the distribution of sample data of the different classes based on IEMLLE is higher than that based on locally linear embedding (LLE) algorithm. Moreover, this article proposes a weighted kernel extreme learning machine (CWKELM) algorithm, among which the use of kernel functions instead of hidden layer random feature maps containing activation functions is beneficial for improving the nonlinear processing ability and robustness of weighted extreme learning machine, and the chaos particle swarm optimization (CPSO) algorithm is proposed to optimize the penalty factor and the kernel parameter of weighted kernel extreme learning machine. The experimental results show that IEMLLE-CWKELM is the higher network intrusion detection accuracy than LLE-CWKELM, LLE-ELM, and principal component analysis- extreme learning machine (PCA-ELM).

show abstract

Section: Introductionmentioning

confidence: 99%