1 Citation (Scopus)

Abstract

Intrusion Detection System helps catch dangerous incoming packets to a computer network. Despite its substantial role, achieving a high-performance system is still challenging, which may cause insecure whole computer networks. Therefore, a reliable system, which can recognize such threatening attacks, is required. Inspired by previous studies, in this research, we take the Autoencoder to extract and reduce the packet’s features and then analyze the results using the Softmax classifier. Furthermore, we remove dropouts and increase the number of batches. The experimental results show that this approach can improve the system's performance. Nevertheless, some works should still be carried out in the future to increase the system’s reliability.

Original languageEnglish
Title of host publicationHybrid Intelligent Systems - 22nd International Conference on Hybrid Intelligent Systems HIS 2022
EditorsAjith Abraham, Ajith Abraham, Tzung-Pei Hong, Ketan Kotecha, Kun Ma, Pooja Manghirmalani Mishra, Niketa Gandhi
PublisherSpringer Science and Business Media Deutschland GmbH
Pages1235-1243
Number of pages9
ISBN (Print)9783031274084
DOIs
Publication statusPublished - 2023
Event22nd International Conference on Hybrid Intelligent Systems, HIS 2022 and the 18th International Conference on Information Assurance and Security, IAS 2022 - Virtual, Online
Duration: 13 Dec 202215 Dec 2022

Publication series

NameLecture Notes in Networks and Systems
Volume647 LNNS
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

Conference22nd International Conference on Hybrid Intelligent Systems, HIS 2022 and the 18th International Conference on Information Assurance and Security, IAS 2022
CityVirtual, Online
Period13/12/2215/12/22

Keywords

  • Autoencoder
  • Feature Extraction
  • IDS
  • Intrusion
  • Network Infrastructure
  • Network Security

Fingerprint

Dive into the research topics of 'Implementing Autoencoder Compression to Intrusion Detection System'. Together they form a unique fingerprint.

Cite this