• Home
  • Search
  • Towards Robust Intrusion Detection: Exploring Feature Selection, Balancing Strategies, and Deep Learning for Minority Class Optimization
  • https://doi.org/10.14569/ijacsa.2026.0170104Copy DOI Icon

Towards Robust Intrusion Detection: Exploring Feature Selection, Balancing Strategies, and Deep Learning for Minority Class Optimization

  • Abstract
  • Literature Map
  • Similar Papers
Abstract

The increasing connectivity of systems and the rapid growth of the Internet have intensified cybersecurity threats. It has been demonstrated that conventional signature-based intrusion detection methods are deficient, especially against Zero-Day attacks. An alternative approach involves the deployment of Intrusion Detection Systems (IDS) that are based on deep learning algorithms. However, these systems face a significant challenge in detecting minority classes of attacks, such as Remote-to-Local (R2L) and User-to-Root (U2R) attacks, which, although rare, are of critical importance. Misclassifying these attacks is costly. Therefore, the reduction of false negatives is achieved by coupling feature selection techniques (Chi square, correlation, information Gain, Extreme Gradient Boosting (XGBoost), Autoencoder), oversampling methods (Synthetic Minority Oversampling Technique (SMOTE), Adaptive Synthetic Sampling (ADASYN)) and deep learning models (Deep Neural Network (DNN), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) and hybrid model CNN LSTM). The present study uses the NSL-KDD dataset, with a particular focus on the minority classes R2L, which represents 2.61% of the dataset, and U2R, representing 0.08% of the dataset. The findings indicate that data balancing is paramount. ADASYN facilitates 100% U2R detection, while SMOTE enhances R2L accuracy to above 95%. The application of correlation and autoencoder feature selection techniques proved to be the most effective. The effectiveness of CNN models in addressing U2R classification tasks has been extensively demonstrated, while the use of DNN or CNN-LSTM models has been shown to yield optimal results for R2L tasks. DNN remains the most stable model overall. For the two minority classes, the most effective pipelines are Correlation + SMOTE + DNN, achieving 93.84 % recall for U2R and 99.88 % for R2L, and Autoencoder + SMOTE + CNN-LSTM, achieving 89.66 % recall for R2L and 99.68 % for U2R.

Similar Papers
  • PDF
  • Research Article
  • Citations33

An Efficient SMOTE-Based Deep Learning Model for Voice Pathology Detection

  • Mar 10, 2023
  • Applied Sciences
  • Ji-Na Lee +1
  • Dissertation

Improveing F-beta Score in Classifying Shark Data into Shark Behaviors

  • Jan 01, 2024
  • Ibrahim M Ali
  • Research Article
  • Citations1

Enhanced Chronic Kidney Disease Detection Using Deep Learning: A Comparative Analysis of CNN and LSTM Models.

  • Mar 29, 2025
  • Journal of Information Systems Engineering and Management
  • Gaurav G Katkar, Shilpa Shinde
  • Research Article
  • Citations10

Enhancing the prediction of IDC breast cancer staging from gene expression profiles using hybrid feature selection methods and deep learning architecture.

  • Aug 02, 2023
  • Medical & Biological Engineering & Computing
  • Akash Kishore +4
  • PDF
  • Research Article
  • Citations14

Evaluating Uses of Deep Learning Methods for Causal Inference

  • Jan 01, 2022
  • IEEE Access
  • Albert Whata +1
  • Book Chapter
  • Citations5

Comparative Multinomial Text Classification Analysis of Naïve Bayes and XGBoost with SMOTE on Imbalanced Dataset

  • Sep 05, 2021
  • Ashish Chaturvedi +3
  • Conference Article
  • Citations12

Data Balancing and CNN based Network Intrusion Detection System

  • Mar 01, 2023
  • Omar Elghalhoud +3
  • Research Article

Performance evaluation of SFP models using ML/DL and feature selection via cost evaluation framework.

  • Jul 13, 2026
  • Scientific reports
  • Sonika Rathi +3
  • Research Article

Ensemble Deep Learning with Data Resampling for Enhanced Credit Card Fraud Detection

  • Jan 01, 2026
  • International Journal of Research and Innovation in Applied Science
  • Mrs.Sangamithrai +2
  • Research Article

AI-BASED INTRUSION DETECTION FRAMEWORK

  • Jan 12, 2026
  • Iraqi Journal of Intelligent Computing and Informatics (IJICI)
  • Ali Raed Alsultani
  • Research Article
  • Citations342

An effective convolutional neural network based on SMOTE and Gaussian mixture model for intrusion detection in imbalanced dataset

  • May 16, 2020
  • Computer Networks
  • Hongpo Zhang +3
  • PDF
  • Research Article
  • Citations101

Enhanced Intrusion Detection with LSTM-Based Model, Feature Selection, and SMOTE for Imbalanced Data

  • Jan 05, 2024
  • Applied Sciences
  • Hussein Ridha Sayegh +2
  • Research Article
  • Citations21

Ensemble-Based Machine Learning Algorithm for Loan Default Risk Prediction

  • Oct 31, 2024
  • Mathematics
  • Abisola Akinjole +4
  • Research Article
  • Citations22

Classification of Imbalanced Data Using SMOTE and AutoEncoder Based Deep Convolutional Neural Network

  • Jun 01, 2023
  • International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems
  • Suja A Alex +1
  • Conference Article
  • Citations2

Hyperspectral image classification with imbalanced data based on oversampling and convolutional neural network

  • Dec 18, 2019
  • Lei Cai +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.