Preliminary Results in Using Attention for Increasing Attack Identification Efficiency

Forskningsoutput: Kapitel i bok/konferenshandlingKonferensbidragVetenskapligPeer review

1 Citeringar (Scopus)
123 Nedladdningar (Pure)

Sammanfattning

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.
OriginalspråkEngelska
Titel på värdpublikation2023 IEEE International Conference on Software Testing, Verification and Validation
FörlagIEEE
Sidor159-164
Antal sidor6
ISBN (tryckt)979-8-3503-3336-7
DOI
StatusPublicerad - maj 2023
MoE-publikationstypA4 Artikel i en konferenspublikation
EvenemangIEEE International Conference on Software Testing, Verification and Validation - Dublin, Irland
Varaktighet: 16 apr. 202320 apr. 2023
Konferensnummer: 16
https://conf.researchr.org/home/icst-2023

Publikationsserier

NamnIEEE International Conference on Software Testing, Verification and Validation Workshops
FörlagIEEE
ISSN (tryckt)2159-4848

Konferens

KonferensIEEE International Conference on Software Testing, Verification and Validation
Förkortad titelICST
Land/TerritoriumIrland
OrtDublin
Period16/04/2320/04/23
Internetadress

Fingeravtryck

Fördjupa i forskningsämnen för ”Preliminary Results in Using Attention for Increasing Attack Identification Efficiency”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här