In 2014, we launched our open-access repository which offers full text access to conference proceedings from many of our events including the INC and HAISA series. These papers are free to access and distribute (subject to citing the source).
Tenth International Network Conference (INC 2014)
Title: A Self-Learning Network Anomaly Detection System using Majority Voting
Author(s): Denis Hock, Martin Kappes
Keywords: Anomaly Detection, Self-Learning, Majority Voting, Replacement Strategies
Abstract: Network traffic is constantly changing. However, many current Intrusion Detection Systems require somewhat static conditions in order to work properly. In this paper, we propose ongoing training and updating procedures and introduce a self-learning Anomaly Detection System based on majority voting that can adapt to network changes by steadily exchanging small parts of training data and evaluate the performance of different replacement strategies for this process.
Download count: 1194
How to get this paper:
PDF copy of this paper is free to download. You may distribute this copy providing you cite this page as the source.