Robust Preprocessing and Random Forests Technique for Network Probe Anomaly Detection
G. Sunil Kumar1, C. V. K Sirisha2, Kanaka Durga. R3, A. Devi4
1G. Sunil Kumar, Departemnt of Computer Applications, Maris Stella College, Vijayawada, A.P., India.
2G. Sunil Kumar, Departemnt of Computer Applications, Maris Stella College, Vijayawada, A.P., India.
3G. Sunil Kumar, Departemnt of Computer Applications, Maris Stella College, Vijayawada, A.P., India.
4G. Sunil Kumar, Departemnt of Computer Applications, Maris Stella College, Vijayawada, A.P., India.
Manuscript received on December 10, 2011. | Revised Manuscript received on December 27, 2011. | Manuscript published on January 05, 2012. | PP: 391-395 | Volume-1 Issue-6, January 2012. | Retrieval Number: F0350121611/2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: During the past few years, huge amount of network attacks have increased the requirement of efficient network intrusion détection techniques. Different classification techniques for identifying various real time network attacks have been proposed in the literature. But most of the algorithms fail to classify the new type of attacks due to lack of collaborative filtering technique and robust classifiers. In this project we propose a new collaborating filtering technique for preprocessing the probe type of attacks and implement a hybrid classifiers based on binary particle swarm optimization (BPSO) and random forests (RF) algorithm for the classification of PROBE attacks in a network. PSO is an optimization method which has a strong global search capability and is used for fine-tuning of the features whereas RF, a highly accurate classifier, is used here for Probe type of attacks classification.
Keywords: Random forest, self organizing map, intrusion
detection, filtering, Normalization.