Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal International Journal of Informatics and Communication Technology (IJ-ICT) Indonesian Journal of Electrical Engineering and Computer Science
Perumal, Rajakumar
Unknown Affiliation
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Enhancing network security using unsupervised learning approach to combat zero-day attack Perumal, Rajakumar; Karuppiah, Tamilarasi; Panneerselvam, Uppiliraja; Annamalai, Venkatesan; Kaliyaperumal, Prabu
Indonesian Journal of Electrical Engineering and Computer Science Vol 36, No 2: November 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v36.i2.pp1284-1293

Abstract

Machine learning (ML) and advanced neural network methodologies like deep learning (DL) techniques have been increasingly utilized in developing intrusion detection systems (IDS). However, the growing quantity and diversity of cyber-attacks pose a significant challenge for IDS solutions reliant on historical attack signatures. This highlights the industry's need for resilient IDSs that can identify zero-day attacks. Current studies focusing on outlier-based zero-day detection are hindered by elevated false-negative rates, thereby constraining their practical efficacy. This paper suggests utilizing an autoencoder (AE) approach for zero-day attack detection, aiming to achieve high recall while minimizing false negatives. Evaluation is conducted using well-established IDS datasets, CICIDS2017 and CSECICIDS2018. The model's efficacy is demonstrated by contrasting its performance with that of a one-class support vector machine (OCSVM). The research underscores the OCSVM's capability in distinguishing zero-day attacks from normal behavior. Leveraging the encoding-decoding capabilities of AEs, the proposed model exhibits promising results in detecting complex zero-day attacks, achieving accuracies ranging from 93% to 99% across datasets. Finally, the paper discusses the balance between recall and fallout, offering valuable insights into model performance.
A hybrid framework for enhanced intrusion detection in cloud environments leveraging autoencoder Alagarsamy, Abinaya; Elumalai, Thenmozhi; Ramesh, S. P.; Karuppiah, Tamilarasi; Kaliyaperumal, Prabu; Perumal, Rajakumar
International Journal of Informatics and Communication Technology (IJ-ICT) Vol 14, No 2: August 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijict.v14i2.pp555-564

Abstract

In today’s world, the significance of network security and cloud environments has grown. The rising demand for data transmission, along with the versatility of cloud-based solutions and widespread availability of global resources, are key drivers of this growth. In response to rapidly evolving threats and malicious attacks, developing a robust intrusion detection system (IDS) is essential. This study addresses the imbalanced data and utilizes an unsupervised learning approach to protect network data. The suggested hybrid framework employs the CIC-IDS2017 dataset, integrating methods for handling imbalanced data with unsupervised learning to enhance security. Following preprocessing, principal component analysis (PCA) reduces the dimensionality from eighty features to twenty-three features. The extracted features are input into density-based spatial clustering of applications with noise (DBSCAN), a clustering algorithm. particle swarm optimization (PSO) optimizes DBSCAN, grouping similar traffic and enhancing classification. To address the imbalances in the learning process, the autoencoder (AE) algorithm demonstrates unsupervised learning. The data from the cluster is input into the AE, a deep learning algorithm, which classifies traffic as normal or an attack. The proposed approach (PCA+DBSCAN+AE) attains remarkable intrusion detection accuracy exceeding 98%, and outperforms five contemporary methodologies.
Co-Authors Alagarsamy, Abinaya Annamalai, Venkatesan Elumalai, Thenmozhi Kaliyaperumal, Prabu Karuppiah, Tamilarasi Panneerselvam, Uppiliraja Ramesh, S. P.