Data Reduction for Optimizing Feature Selection in Modeling Intrusion Detection System

Abstract

With the development and ease of access to internet networks, the potential for attacks and intrusions have increased. The intrusion detection system (IDS), an approach to overcome this problem, is grouped into two models: signature-based and anomaly-based. An anomaly-based IDS can be implemented by machine learning; one of the schemes in machine learning is data reduction. IDS datasets are usually obtained through a real-time process that has undefined proportional data. The purpose of data reduction is to speed up and optimize the process, improving accuracy, precision, and specifications. There are several methods to perform data reduction, one of which uses outlier detection techniques. Proper outlier detection has a positive impact on improving the classification results of machine learning. In this research, the outlier detection is done by a circle generated from the k -means clustering of all selected features. Two scenarios are designed for the evaluation: a circle generated from two points of the minimum and maximum cluster and median of all clusters. The formation of clusters conducted by k -means clustering determines the size and direction of the outlier circle so that it dynamically adjusts the distribution of data from the feature selection results. By employing the previous feature selection algorithms, the comparison is performed to evaluate the proposed method's performance. Our empirical results show that the second scenario can significantly improve the classification results in terms of accuracy, detection rate, and precision. The first and second experiments can increase the accuracy by 0.02%, and the third experiment is by 0.1%. The detection rate in the first, second, and third experiments increases by 0.01%, 0.02%, and 0.07. At the same time, precision increases by 0.04%, 0.02%, and 0.01%, correspondingly.

Optimization of Intrusion Detection Systems Determined by Ameliorated HNADAM-SGD Algorithm

“…In the recent research trends, it has been observed that the method of feature selection is modified to boost the classification performance of the designed model. It has been found by [5], that, based on features selection and data reduction, the classification performance of the model enhances. The authors performed a test on three different sets of features to validate its hypothesis of enhancing the performance of a model on the basis of different features, and the performance of classification model became faster when the size of data was small.…”

“…The Figure 3 represents the HNADAM-SDG flow chart, having a tendency to lower itself during convergence, and is represented using variable momentum and a step size, as in Equation ( 18) [5].…”

“…The differentiation is separately obtained for a and b, having derivative to be zero. The a and b estimates are defined in Equations ( 19)-( 21) [5].…”

Optimization of Intrusion Detection Systems Determined by Ameliorated HNADAM-SGD Algorithm

“…The In the recent research trends it is been observed that the method of feature selection is modified to enhance the classification performance of the designed model. It has been found by (Iman and Ahmad, 2020) A hybrid approach has been introduced by (Pokuri., 2021) for analysing IDS using Naïve Bayes and improved BAT algorithm by analysing selected features. The author validates the hypothesis that the feature section methodology improves the performance of the anomaly detection model.…”

ANOVA-SVM for Selecting Subset Features in Encrypted Internet Traffic Classification

“…These amount and irrelevant feature problems in the dataset can be overcome by performing data preprocessing, such as feature selection [11][12][13] and data reduction [14][15][16]. Feature selection is used to remove unused features (x-dimensions) from the dataset, while data reduction is to remove unused data (ydimensions) from the dataset.…”