Skip to main navigation Skip to search Skip to main content

Network Attack Detection Method Based on Convolutional Neural Network

  • Nan Ding
  • , Yang Liu*
  • , Yimin Fan
  • , Dangyang Jie
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The existing traditional network attack detection algorithms have low detection accuracy and are difficult to cope with external malicious and capricious network attacks in the communication and control systems. In order to solve this problem, this paper designs a network attack detection method based on convolutional neural network technology, which improves the recognition accuracy of attack detection for network attack signals. Specifically, a convolutional neural network structure with overlapping pooling layers is designed, and the improved data preprocessing method and parameter tuning make the recognition accuracy of the obtained convolution network on the KDD99 data set greatly improved. Finally, the experimental results show that the proposed network tuning strategy is effective, and the neural network structure designed in this paper is superior to other existing intelligent detection algorithms in terms of recognition accuracy.

Original languageEnglish
Title of host publicationProceedings of 2019 Chinese Intelligent Systems Conference - Volume II
EditorsYingmin Jia, Junping Du, Weicun Zhang
PublisherSpringer Verlag
Pages610-620
Number of pages11
ISBN (Print)9789813296855
DOIs
StatePublished - 2020
EventChinese Intelligent Systems Conference, CISC 2019 - Haikou, China
Duration: 26 Oct 201927 Oct 2019

Publication series

NameLecture Notes in Electrical Engineering
Volume593
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceChinese Intelligent Systems Conference, CISC 2019
Country/TerritoryChina
CityHaikou
Period26/10/1927/10/19

Keywords

  • Attack detection system
  • Convolutional neural network
  • Deep learning
  • Network environment

Fingerprint

Dive into the research topics of 'Network Attack Detection Method Based on Convolutional Neural Network'. Together they form a unique fingerprint.

Cite this