• English
  • Deutsch
  • Log In
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Explanation Framework for Intrusion Detection
 
  • Details
  • Full
Options
2021
  • Konferenzbeitrag

Titel

Explanation Framework for Intrusion Detection

Abstract
Machine learning and deep learning are widely used in various applications to assist or even replace human reasoning. For instance, a machine learning based intrusion detection system (IDS) monitors a network for malicious activity or specific policy violations. We propose that IDSs should attach a sufficiently understandable report to each alert to allow the operator to review them more efficiently. This work aims at complementing an IDS by means of a framework to create explanations. The explanations support the human operator in understanding alerts and reveal potential false positives. The focus lies on counterfactual instances and explanations based on locally faithful decision-boundaries.
Author(s)
Burkart, Nadia
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Franz, Maximilian
Huber, Marco F.
Fraunhofer-Institut für Produktionstechnik und Automatisierung IPA
Hauptwerk
Machine Learning for Cyber Physical Systems
Konferenz
International Conference on Machine Learning for Cyber Physical Systems (ML4CPS) 2020
DOI
10.1007/978-3-662-62746-4_9
File(s)
N-621355.pdf (429.6 KB)
Language
Englisch
google-scholar
IOSB
IPA
Tags
  • intrusion detection

  • Explainable Machine L...

  • Counterfactual Explan...

  • detection

  • Explainable Artificia...

  • maschinelles Lernen

  • Künstliche Intelligen...

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022