Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Explanation Framework for Intrusion Detection

: Burkart, Nadia; Franz, Maximilian; Huber, Marco F.

Fulltext urn:nbn:de:0011-n-6213553 (429 KByte PDF)
MD5 Fingerprint: 671f01c5bcf3abaf0a291f12407a5ed1
(CC) by
Created on: 15.1.2021

Beyerer, J.:
Machine Learning for Cyber Physical Systems : Selected papers from the International Conference ML4CPS 2020, Berlin, March 12-13, 2020
Cham: Springer Nature, 2021 (Technologien für die intelligente Automation 13)
ISBN: 978-3-662-62745-7
ISBN: 978-3-662-62746-4
International Conference on Machine Learning for Cyber Physical Systems (ML4CPS) <5, 2020, Berlin>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()
Fraunhofer IPA ()
intrusion detection; Explainable Machine Learning; Counterfactual Explanations; detection; Explainable Artificial Intelligence (XAI); maschinelles Lernen; Künstliche Intelligenz

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.