Plusmine: Dynamic Active Learning with Semi-Supervised Learning for Automatic Classification

Jan Klein; Sandjai Bhulai; Mark Hoogendoorn; Rob Van Der Mei

doi:10.1145/3486622.3493948

Plusmine: Dynamic Active Learning with Semi-Supervised Learning for Automatic Classification

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

Abstract

A major problem in cybersecurity research is the correct labeling of up-to-date datasets. It relies on the availability of human experts, and is as such very cumbersome. Motivated by this, two techniques have been proposed for efficient labeling: Active Learning (AL) and Semi-Supervised Learning (SeSL). In this paper, we introduce Plusmine: an intrusion detection method that combines the benefits of AL and SeSL to efficiently automate classification. We develop new techniques for both components. Moreover, we empirically show that Plusmine obtains good and more robust results than benchmark methods.

Original language	English
Title of host publication	WI-IAT '21
Subtitle of host publication	IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology
Publisher	Association for Computing Machinery
Pages	146-153
Number of pages	8
ISBN (Electronic)	9781450391153
DOIs	https://doi.org/10.1145/3486622.3493948
Publication status	Published - Dec 2021
Event	2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021 - Virtual, Online, Australia Duration: 14 Dec 2021 → 17 Dec 2021

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021
Country/Territory	Australia
City	Virtual, Online
Period	14/12/21 → 17/12/21

Bibliographical note

Publisher Copyright:
© 2021 Owner/Author.

Keywords

active learning
automatic labeling
network intrusion detection
partially labeled
semi-supervised learning

Access to Document

10.1145/3486622.3493948

Persistent URL (handle)

Persistent link

Cite this

Klein, J., Bhulai, S., Hoogendoorn, M., & Van Der Mei, R. (2021). Plusmine: Dynamic Active Learning with Semi-Supervised Learning for Automatic Classification. In WI-IAT '21: IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (pp. 146-153). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3486622.3493948

@inproceedings{74e721335bb34807b2a852b87e593303,

title = "Plusmine: Dynamic Active Learning with Semi-Supervised Learning for Automatic Classification",

abstract = "A major problem in cybersecurity research is the correct labeling of up-to-date datasets. It relies on the availability of human experts, and is as such very cumbersome. Motivated by this, two techniques have been proposed for efficient labeling: Active Learning (AL) and Semi-Supervised Learning (SeSL). In this paper, we introduce Plusmine: an intrusion detection method that combines the benefits of AL and SeSL to efficiently automate classification. We develop new techniques for both components. Moreover, we empirically show that Plusmine obtains good and more robust results than benchmark methods. ",

keywords = "active learning, automatic labeling, network intrusion detection, partially labeled, semi-supervised learning",

author = "Jan Klein and Sandjai Bhulai and Mark Hoogendoorn and \{Van Der Mei\}, Rob",

note = "Publisher Copyright: {\textcopyright} 2021 Owner/Author.; 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021 ; Conference date: 14-12-2021 Through 17-12-2021",

year = "2021",

month = dec,

doi = "10.1145/3486622.3493948",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "146--153",

booktitle = "WI-IAT '21",

}

Klein, J, Bhulai, S , Hoogendoorn, M & Van Der Mei, R 2021, Plusmine: Dynamic Active Learning with Semi-Supervised Learning for Automatic Classification. in WI-IAT '21: IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 146-153, 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021, Virtual, Online, Australia, 14/12/21. https://doi.org/10.1145/3486622.3493948

Plusmine: Dynamic Active Learning with Semi-Supervised Learning for Automatic Classification. / Klein, Jan; Bhulai, Sandjai ; Hoogendoorn, Mark et al.
WI-IAT '21: IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology. Association for Computing Machinery, 2021. p. 146-153 (ACM International Conference Proceeding Series).

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Plusmine: Dynamic Active Learning with Semi-Supervised Learning for Automatic Classification

AU - Klein, Jan

AU - Bhulai, Sandjai

AU - Hoogendoorn, Mark

AU - Van Der Mei, Rob

PY - 2021/12

Y1 - 2021/12

N2 - A major problem in cybersecurity research is the correct labeling of up-to-date datasets. It relies on the availability of human experts, and is as such very cumbersome. Motivated by this, two techniques have been proposed for efficient labeling: Active Learning (AL) and Semi-Supervised Learning (SeSL). In this paper, we introduce Plusmine: an intrusion detection method that combines the benefits of AL and SeSL to efficiently automate classification. We develop new techniques for both components. Moreover, we empirically show that Plusmine obtains good and more robust results than benchmark methods.

AB - A major problem in cybersecurity research is the correct labeling of up-to-date datasets. It relies on the availability of human experts, and is as such very cumbersome. Motivated by this, two techniques have been proposed for efficient labeling: Active Learning (AL) and Semi-Supervised Learning (SeSL). In this paper, we introduce Plusmine: an intrusion detection method that combines the benefits of AL and SeSL to efficiently automate classification. We develop new techniques for both components. Moreover, we empirically show that Plusmine obtains good and more robust results than benchmark methods.

KW - active learning

KW - automatic labeling

KW - network intrusion detection

KW - partially labeled

KW - semi-supervised learning

UR - https://www.scopus.com/pages/publications/85128612566

UR - https://www.scopus.com/pages/publications/85128612566#tab=citedBy

U2 - 10.1145/3486622.3493948

DO - 10.1145/3486622.3493948

M3 - Conference contribution

AN - SCOPUS:85128612566

T3 - ACM International Conference Proceeding Series

SP - 146

EP - 153

BT - WI-IAT '21

PB - Association for Computing Machinery

T2 - 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021

Y2 - 14 December 2021 through 17 December 2021

ER -

Klein J, Bhulai S , Hoogendoorn M , Van Der Mei R. Plusmine: Dynamic Active Learning with Semi-Supervised Learning for Automatic Classification. In WI-IAT '21: IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology. Association for Computing Machinery. 2021. p. 146-153. (ACM International Conference Proceeding Series). doi: 10.1145/3486622.3493948

Plusmine: Dynamic Active Learning with Semi-Supervised Learning for Automatic Classification

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this