Incremental Open Set Intrusion Recognition Using Extreme Value Machine
Authors:
- James HenrydossJHJames Henrydoss
- Steve CruzSCSteve Cruz
- Ethan M. RuddEREthan M. Rudd
- Manuel GuntherMGManuel Gunther
- Terrance E. BoultTBTerrance E. Boult
- 1 December 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1089-1093
Abstract
Typically, most network intrusion detection systems use supervised learning techniques to identify network anomalies. A problem exists when identifying the unknowns and automatically updating a classifier with new query classes. This is defined as an open set incremental learning problem and we propose to extend a recently introduced method, the Extreme Value Machine (EVM) to address the issue of identifying new classes during query time. The EVM is derived from the statistical extreme value theory and is the first classifier that can perform kernel-free, nonlinear, variable bandwidth outlier detection combined with incremental learning. In this paper, we utilize the EVM for intrusion detection and measure the open set recognition performance of identifying known and unknown classes. Additionally, we evaluate the performance on the KDDCUP'99 dataset and compare the results with the state-of-the-art Weibull-SVM (W-SVM). Our findings demonstrate that the EVM mirrors the performance of the W-SVM classifier, while it supports incremental learning.Keywords
This publication has 13 references indexed in Scilit:
- Toward Open-Set Face Recognition2017
- Open set intrusion recognition for fine-grained attack categorization2017
- A Survey of Stealth Malware Attacks, Mitigation Measures, and Steps Toward Autonomous Open World SolutionsIEEE Communications Surveys & Tutorials, 2016
- Probability Models for Open Set RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Multi-class Open Set Recognition Using Probability of Inclusion2014
- Toward Open Set RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Robust Fusion: Extreme Value Theory for Recognition Score Normalization2010
- Intrusion detection by machine learning: A reviewExpert Systems with Applications, 2009
- A detailed analysis of the KDD CUP 99 data set2009
- Bertrand's Paradox and the Principle of IndifferencePhilosophy of Science, 2007