Active learning for network intrusion detection

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Authors

Anomaly detection for network intrusion detection is usually considered an unsupervised task. Prominent techniques, such as one-class support vector machines, learn a hypersphere enclosing network data, mapped to a vector space, such that points outside of the ball are considered anomalous. However, this setup ignores relevant information such as expert and background knowledge. In this paper, we rephrase anomaly detection as an active learning task. We propose an effective active learning strategy to query low-confidence observations and to expand the data basis with minimal labeling effort. Our empirical evaluation on network intrusion detection shows that our approach consistently outperforms existing methods in relevant scenarios.
OriginalspracheEnglisch
TitelAISec '09 : Proceedings of the ACM Conference on Computer and Communications Security
HerausgeberDirk Balfanz, Jessica Staddon
Anzahl der Seiten8
ErscheinungsortNew York
VerlagAssociation for Computing Machinery, Inc
Erscheinungsdatum09.11.2009
Seiten47-54
ISBN (Print)978-1-60558-781-3
DOIs
PublikationsstatusErschienen - 09.11.2009
Extern publiziertJa
Veranstaltung2nd ACM Workshop on Security and Artificial Intelligence, AISec '09, Co-located with the 16th ACM Computer and Communications Security Conference - Chicago, USA / Vereinigte Staaten
Dauer: 09.11.200913.11.2009
Konferenznummer: 2

DOI

Zuletzt angesehen

Forschende

  1. Christian Pfeifer

Publikationen

  1. Repeat Receipts: A device for generating visible data in market research focus groups
  2. E-stability and stability of adaptive learning in models with private information
  3. Emotion Prediction by Facial Expressions in Human-Computer Interfaces
  4. The Radius of Trust Problem Remains Resolved
  5. Web 2.0 Tasks in Action
  6. Experience from downscaling IPCC-SRES scenarios to specific national-level focus scenarios for ecosystem service management
  7. Ecosystem functions as indicators for heathland responses to nitrogen fertilisation
  8. Introduction
  9. Development and criterion validity of differentiated and elevated vocational interests in adolescence
  10. Intra-Individual Value Change in Adulthood
  11. Sustainability Science with Ozzy Osbourne, Julia Roberts and Ai Weiwei
  12. The relationship between acculturation strategies and depressive and anxiety disorders in Turkish migrants in the Netherlands
  13. Ein un(mögliches) Programm
  14. Knowledge acquisition and development in sustainability-oriented small and medium-sized enterprises
  15. Mathematical Chemistry and Chemoinformatics
  16. Stabilizing the grid with regional virtual power plants
  17. Separating Cognitive and Content Domains in Mathematical Competence
  18. Method for the determination of specific molecular markers of biomass burning in lake sediments
  19. Politics after Networks
  20. The Role of Assessment and Quality Management in Transformations towards Sustainable Development
  21. Top-down biological motion perception does not differ between adults scoring high versus low on autism traits
  22. An empirical note on commuting distance and sleep during workweek and weekend
  23. Local levers for change
  24. How should we fund open access monographs and what do you think is the most likely way that funding will happen?
  25. Strategy execution in hospitals
  26. ‘Then you just have to perform better’
  27. Synthesis, self-assembly, bacterial and fungal toxicity, and preliminary biodegradation studies of a series of L-phenylalanine-derived surface-active ionic liquids
  28. Introduction
  29. Flexible and Adaptable Restoration
  30. Work in Progres Work on Progress
  31. Is there a compensating wage differential for high crime levels?
  32. Evaluation of a temporal causal model for predicting the mood of clients in an online therapy
  33. Embodying relationality through immersive sustainability solutions with Indigenous communities in the Ecuadorian Amazon

Presse / Medien

  1. Public Value im Internet