Title: Intelligent intrusion detection system using log cluster decision tree detection mitigation in complex event processing
Authors: S. Sandosh; V. Govindasamy; G. Akila
Addresses: Department of Computer Science and Engineering, Pondicherry Engineering College, Pondicherry, India ' Department of Information Technology, Pondicherry Engineering College, Pondicherry, India ' Department of Computer Science and Engineering, Pondicherry Engineering College, Pondicherry, India
Abstract: The world of technology largely engages on the networks that provide the vast amount of data for the user all around the world. The networks can be of different domains that includes education, market or even defence. Hence the network has to be secure against any attacks that lead to intrusion. For securing the networks, several intrusion detection systems (IDS) are developed, however the possibility of intrusion remains in the networks. In the current work, we propose the novel intelligent IDS with log cluster decision tree detection mitigation (IIDS-LCDTDM) technique in complex event processing environment, an extension of our previous work. The novel system comprises of three major algorithms, attribute greedy stepwise selection, two-mean-log cluster along with tree detection, and mitigation algorithm. The gure6percent dataset is used to evaluate the proposed algorithm for various performance metrics using Java/J2EE software. From the evaluation result, the proposed system provided the accuracy of 99.987%, which was better than our previous model with 99.9463%.
Keywords: intrusion detection system; complex event processing; performance metrics; IIDS-LCDTDM.
International Journal of Internet Technology and Secured Transactions, 2021 Vol.11 No.4, pp.352 - 368
Received: 08 Oct 2019
Accepted: 27 Mar 2020
Published online: 01 Aug 2021 *