A Survey on Methods and Datasets of Intrusion Detection System (IDS) In Deep Learning

Fuente: Zenodo
Saved in:
Bibliographic Details
Main Authors: J Archana, Dr. A S Aneetha
Format: Recurso digital
Published: Zenodo 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866901414160105472
author J Archana
Dr. A S Aneetha
author_facet J Archana
Dr. A S Aneetha
contents Due to the advent of a limitless communication paradigm and an increase in the number of networked digital devices in recent years, there has been a rising concern about cybersecurity, which attempts to protect either the system's information or communication technology. Intruders develop new attack types on a daily basis; consequently, in order to prevent these attacks, they must initially be precisely detected by the intrusion detection systems (IDSs) in use, and then appropriate responses must be provided. IDSs, which serve as vital for network security, are made up of three basic components: data collecting, feature selection/conversion, and a decision engine. The final component has a direct impact on system efficiency, and the employment of machine learning techniques is one of the most intriguing research fields. Deep learning has recently evolved as a novel approach that, through its own unique learning process, permits the utilization of Big Data with a low training time and high accuracy rate. As a result, it has begun to be used in intrusion detection systems. In this paper, it research aims to explore deep learning-based intrusion detection system approaches by doing a study of the literature and providing prior knowledge in either deep learning algorithms or intrusion detection systems.
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_18277320
institution Zenodo
language
publishDate 2023
publisher Zenodo
record_format zenodo
spellingShingle A Survey on Methods and Datasets of Intrusion Detection System (IDS) In Deep Learning
J Archana
Dr. A S Aneetha
intrusion detection systems
network security
Deep learning
real-time attackers. Introduction
Due to the advent of a limitless communication paradigm and an increase in the number of networked digital devices in recent years, there has been a rising concern about cybersecurity, which attempts to protect either the system's information or communication technology. Intruders develop new attack types on a daily basis; consequently, in order to prevent these attacks, they must initially be precisely detected by the intrusion detection systems (IDSs) in use, and then appropriate responses must be provided. IDSs, which serve as vital for network security, are made up of three basic components: data collecting, feature selection/conversion, and a decision engine. The final component has a direct impact on system efficiency, and the employment of machine learning techniques is one of the most intriguing research fields. Deep learning has recently evolved as a novel approach that, through its own unique learning process, permits the utilization of Big Data with a low training time and high accuracy rate. As a result, it has begun to be used in intrusion detection systems. In this paper, it research aims to explore deep learning-based intrusion detection system approaches by doing a study of the literature and providing prior knowledge in either deep learning algorithms or intrusion detection systems.
title A Survey on Methods and Datasets of Intrusion Detection System (IDS) In Deep Learning
topic intrusion detection systems
network security
Deep learning
real-time attackers. Introduction
url https://doi.org/10.5281/zenodo.18277320