Feature Selection Method for Ml/Dl Classification of Network Attacks in Digital Forensics

The research is related to machine learning and deep learning (ML/DL) methods for clustering and classification that are compatible with anomaly detection (network attacks detection) in digital forensics. Research is conducted in the field of selecting subsets of features of a dataset useful for con...

Full description

Saved in:
Bibliographic Details
Published inTransport and telecommunication Vol. 23; no. 2; pp. 131 - 141
Main Authors Grakovski, Alexander, Krivchenkov, Aleksandr, Misnevs, Boriss
Format Journal Article
LanguageEnglish
Published Riga Sciendo 01.04.2022
De Gruyter Poland
Subjects
AHP
Algorithms
Analytic hierarchy process
ANN
Anomalies
anomaly detection
Artificial neural networks
Classification
Classifiers
Clustering
Computer forensics
Deep learning
Feature selection
Forensic computing
Forensic sciences
IDS
Iterative methods
Learning theory
Machine learning
Online AccessGet full text

Cover

More Information
Summary:The research is related to machine learning and deep learning (ML/DL) methods for clustering and classification that are compatible with anomaly detection (network attacks detection) in digital forensics. Research is conducted in the field of selecting subsets of features of a dataset useful for constructing a good predictor (classifier). In this study, a new feature selection method for a classifier based on the Analytical Hierarchy Process (AHP) method is presented and tested. The proposed step-by-step algorithm for the iterative selection of these features makes it possible to obtain the minimum required list of features that are associated with attack events and can be used to detect them. For the classification, Artificial Neural Network (ANN) method is used. The accuracy of attack detection by the proposed method has been verified in numerical experiments.
ISSN:1407-6179
1407-6160
1407-6179
DOI:10.2478/ttj-2022-0011