Selecting Scalable Network Features for Infiltration Detection

Phillip Kendrick, Abir Hussain, Natalia Criado, Martin Randles

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

Abstract

The objective of this study is to explore feature selection for the detection of internal intruders within a local network during the early stages of an attack. As the sophistication of attackers increase, current security systems have proven incapable of detecting advanced stealthy attackers whose aim is to compromise internal networks and remain undetected. We study the available features that are commonly used during network-layer attacker detection and propose two new features to model the extent to which a given networked endpoint conforms with network traffic norms. The proposed features are analysed using several attribute evaluation methods to compare the predictiveness of commonly used features. The results of the analysis show that the proposed features are highly predictive and work towards overcoming the identified deployability issues of previous systems.

Original languageEnglish
Title of host publicationProceedings - 2017 10th International Conference on Developments in eSystems Engineering, DeSE 2017
EditorsHissam Tawfik, Hani Hamdan, Abir Hussain, Jade Hind, Dhiya Al-Jumeily
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages88-93
Number of pages6
ISBN (Electronic)9781538617212
DOIs
Publication statusPublished - 7 Feb 2018
Event10th International Conference on Developments in eSystems Engineering, DeSE 2017 - Paris, France
Duration: 14 Jun 201716 Jun 2017

Publication series

NameProceedings - International Conference on Developments in eSystems Engineering, DeSE
ISSN (Print)2161-1343

Conference

Conference10th International Conference on Developments in eSystems Engineering, DeSE 2017
Country/TerritoryFrance
CityParis
Period14/06/201716/06/2017

Keywords

  • Feature Selection
  • Network Security
  • Post Compromise Detection

Fingerprint

Dive into the research topics of 'Selecting Scalable Network Features for Infiltration Detection'. Together they form a unique fingerprint.

Cite this