Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Inferensi
Rosyadi, Niam
Institut Teknologi Sepuluh Nopember
Computer Science & IT Decision Sciences, Operations Research & Management Engineering Mathematics Social Sciences

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Intrusion Detection Systems (IDSs) using Multivariate Control Chart Hotelling’s T2 with Dimensional Reduction of Factorial Analysis of Mixed Data (FAMD) and Autoencoder Rifki, Kevin Agung Fernanda; Rosyadi, Niam; Zenklinov, Amanatullah Pandu; Suhermi, Novri
Inferensi Vol 7, No 1 (2024)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v7i1.18751

Abstract

Traditional multivariate control charts for network intrusion detection encounter significant challenges including false alarms due to non-conforming network data traffic distributions, limitations in identifying outlier intrusions caused by masking effects, and handling diverse data types. This paper introduces a T2-based multivariate control chart that leverages dimensional reduction techniques using Factor Analysis of Mixed Data (FAMD) and Autoencoder to address these issues. FAMD reduces data with both quantitative and qualitative variables, while Autoencoder focuses on dimensionality reduction for quantitative variables, enhancing multivariate control chart performance. The proposed chart, a modified T2, is compared to conventional T2 with dimensionality reduction through FAMD and Autoencoder. Results from simulating data using UNSW-NB 15 demonstrate T2's superior performance with dimensionality reduction compared to conventional T2. Under various conditions, conventional control chart T achieves 64% accuracy, T2 with FAMD achieves 74%, and T2 with Autoencoder reaches 76%. Notably, T2 with FAMD excels in detecting normal activity as intrusion compared to Autoencoder. This approach holds promise for improving network intrusion detection accuracy, especially in mixed-data environments.
Co-Authors Rifki, Kevin Agung Fernanda Suhermi, Novri Zenklinov, Amanatullah Pandu