File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Enhancing collaborative intrusion detection via disagreement-based semi-supervised learning in IoT environments

TitleEnhancing collaborative intrusion detection via disagreement-based semi-supervised learning in IoT environments
Authors
KeywordsCollaborative intrusion detection
Semi-supervised learning
False alarm reduction
Detection performance
Internet of things
Issue Date2020
PublisherAcademic Press. The Journal's web site is located at http://www.elsevier.com/locate/jnca
Citation
Journal of Network and Computer Applications, 2020, v. 161, p. article no. 102631 How to Cite?
AbstractCollaborative intrusion detection systems (CIDSs) are developing to improve the detection performance of a single detector in Internet of Things (IoT) networks, through exchanging and sharing data. For anomaly detection, machine learning is an important and essential tool to help identify the deviation between current events and pre-built profile. For a traditional supervised learning classifier, there is a need to provide training examples with ground-truth labels in advance. However, labeled instances are quite limited in real-world IoT scenarios, while unlabeled data/instances are widely available. This is because data labeling is a very expensive process that requires huge human efforts and knowledge inputs. To mitigate this issue, the use of semi-supervised learning algorithms is a promising solution, which can leverage unlabeled data to label data automatically without human intervention. In this work, we focus on semi-supervised learning and design DAS-CIDS, by applying disagreement-based semi-supervised learning algorithm for CIDSs. In the evaluation, we investigate the performance of DAS-CIDS using both datasets and in real IoT network environments, in the aspects of both detection performance and false alarm reduction. The experimental results show that as compared with traditional supervised classifiers, our approach is more effective in detecting intrusions and reducing false alarms by automatically leveraging unlabeled data.
Persistent Identifierhttp://hdl.handle.net/10722/284224
ISSN
2023 Impact Factor: 7.7
2023 SCImago Journal Rankings: 2.417
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorLi, W-
dc.contributor.authorMeng, W-
dc.contributor.authorAu, MH-
dc.date.accessioned2020-07-20T05:57:03Z-
dc.date.available2020-07-20T05:57:03Z-
dc.date.issued2020-
dc.identifier.citationJournal of Network and Computer Applications, 2020, v. 161, p. article no. 102631-
dc.identifier.issn1084-8045-
dc.identifier.urihttp://hdl.handle.net/10722/284224-
dc.description.abstractCollaborative intrusion detection systems (CIDSs) are developing to improve the detection performance of a single detector in Internet of Things (IoT) networks, through exchanging and sharing data. For anomaly detection, machine learning is an important and essential tool to help identify the deviation between current events and pre-built profile. For a traditional supervised learning classifier, there is a need to provide training examples with ground-truth labels in advance. However, labeled instances are quite limited in real-world IoT scenarios, while unlabeled data/instances are widely available. This is because data labeling is a very expensive process that requires huge human efforts and knowledge inputs. To mitigate this issue, the use of semi-supervised learning algorithms is a promising solution, which can leverage unlabeled data to label data automatically without human intervention. In this work, we focus on semi-supervised learning and design DAS-CIDS, by applying disagreement-based semi-supervised learning algorithm for CIDSs. In the evaluation, we investigate the performance of DAS-CIDS using both datasets and in real IoT network environments, in the aspects of both detection performance and false alarm reduction. The experimental results show that as compared with traditional supervised classifiers, our approach is more effective in detecting intrusions and reducing false alarms by automatically leveraging unlabeled data.-
dc.languageeng-
dc.publisherAcademic Press. The Journal's web site is located at http://www.elsevier.com/locate/jnca-
dc.relation.ispartofJournal of Network and Computer Applications-
dc.subjectCollaborative intrusion detection-
dc.subjectSemi-supervised learning-
dc.subjectFalse alarm reduction-
dc.subjectDetection performance-
dc.subjectInternet of things-
dc.titleEnhancing collaborative intrusion detection via disagreement-based semi-supervised learning in IoT environments-
dc.typeArticle-
dc.identifier.emailAu, MH: manhoau@hku.hk-
dc.identifier.authorityAu, MH=rp02638-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.jnca.2020.102631-
dc.identifier.scopuseid_2-s2.0-85082972759-
dc.identifier.hkuros310854-
dc.identifier.volume161-
dc.identifier.spagearticle no. 102631-
dc.identifier.epagearticle no. 102631-
dc.identifier.isiWOS:000534307300002-
dc.publisher.placeUnited Kingdom-
dc.identifier.issnl1084-8045-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats