Home > Research > Publications & Outputs > Anomaly detection in the cloud using data density

Electronic data

  • AD3-paper

    Rights statement: ©2016 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

    Accepted author manuscript, 449 KB, PDF-document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Anomaly detection in the cloud using data density

Research output: Contribution in Book/Report/ProceedingsConference contribution

Published
Publication date27/06/2016
Host publicationCloud Computing (CLOUD), 2016 IEEE 9th International Conference on
PublisherIEEE
Pages616-623
Number of pages8
ISBN (Electronic)9781509026197
ISBN (Print)9781509026203
<mark>Original language</mark>English
EventIEEE International Conference on Cloud Computing - San Francisco, United States

Conference

ConferenceIEEE International Conference on Cloud Computing
Abbreviated titleIEEE Cloud 2016
CountryUnited States
CitySan Francisco
Period27/06/162/07/16
Internet address

Publication series

NameCloud Computing (CLOUD), 2016 IEEE 9th International Conference on
PublisherIEEE
ISSN (Electronic)2159-6190

Conference

ConferenceIEEE International Conference on Cloud Computing
Abbreviated titleIEEE Cloud 2016
CountryUnited States
CitySan Francisco
Period27/06/162/07/16
Internet address

Abstract

Cloud computing is now extremely popular because of its use of elastic resources to provide optimized, cost-effective and on-demand services. However, clouds may be subject to challenges arising from cyber attacks including DoS and malware, as well as from sheer complexity problems that manifest themselves as anomalies. Anomaly detection techniques are used increasingly to improve the resilience of cloud environments and indirectly reduce the cost of recovery from outages. Most anomaly detection techniques are computation ally expensive in a cloud context, and often require problem-specific parameters to be predefined in advance, impairing their use in real-time detection. Aiming to overcome these problems, we propose a technique for anomaly detection based on data density. The density is computed recursively, so the technique is memory-less and unsupervised, and therefore suitable for real-time cloud environments. We demonstrate the efficacy of the proposed technique using an emulated dataset from a testbed,
under various attack types and intensities, and in the face of VM migration. The obtained results, which include precision, recall, accuracy, F-score and G-score, show that network level attacks are detectable with high accuracy.

Bibliographic note

©2016 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.