Preliminary Results in Using Attention for Increasing Attack Identification Efficiency

Research output: Chapter in Book/Conference proceedingConference contributionScientificpeer-review

1 Citation (Scopus)
123 Downloads (Pure)

Abstract

In previous work, we proposed an end-to-end intrusion early detection system to identify network attacks in real-time before they are complete and could cause more damage to the system under attack. To implement the approach, we have used a deep neural network which was trained in a supervised manner to extract relevant features from raw network traffic in order to classify network flows into different types of attacks. In this work, we discuss the initial results of the benefits that an attention mechanism brings to the classification performance and the capacity of the network to detect attacks earlier. We empirically evaluate our approach on the CICIDS2017 dataset. Preliminary results show that the attention mechanism improves both the balanced accuracy of the classifier as well as the early detection of attacks.
Original languageEnglish
Title of host publication2023 IEEE International Conference on Software Testing, Verification and Validation
PublisherIEEE
Pages159-164
Number of pages6
ISBN (Print)979-8-3503-3336-7
DOIs
Publication statusPublished - May 2023
MoE publication typeA4 Article in a conference publication
EventIEEE International Conference on Software Testing, Verification and Validation - Dublin, Ireland
Duration: 16 Apr 202320 Apr 2023
Conference number: 16
https://conf.researchr.org/home/icst-2023

Publication series

NameIEEE International Conference on Software Testing, Verification and Validation Workshops
PublisherIEEE
ISSN (Print)2159-4848

Conference

ConferenceIEEE International Conference on Software Testing, Verification and Validation
Abbreviated titleICST
Country/TerritoryIreland
CityDublin
Period16/04/2320/04/23
Internet address

Keywords

  • Attention Mechanism
  • Deep learning
  • Convolution Neural Network
  • Early Intrusion Detection System

Fingerprint

Dive into the research topics of 'Preliminary Results in Using Attention for Increasing Attack Identification Efficiency'. Together they form a unique fingerprint.

Cite this