Abstract—Due to the fast growth of network systems, abundant intrusive approaches have been grown extensively which are escalating many security and solidity threats. Intrusions Detection Systems (IDS) are security programs to decide whether events and activities occurring in the network are intrusive or legitimate. The purpose of IDS is to identify intrusions in network traffic with low false alarms and high detection rate while consuming lesser resources and computational cost. There are plentiful issues in traditional IDS including regular updating, low detection capability to unknown attacks, high false alarms rate, extraordinary resources consumption and many others. Similarly, Intelligent Network IDS have snags of performance efficiency, false positive and false negative while today’s advance Neural Network approaches are also facing training/learning overhead, high false alarms and low detection rate. Soft computing is an innovative field to develop intelligent IDS while minimizing the deficiencies in other approaches. The objective of this research is to propose an efficient soft computing approach with low false alarms and high detection rate while maintaining low cost and less time. Our research promising results show that a new proposed system is an improved and applicable representation of an ideal intrusion detection system.
Index Terms—IDS, features selection, NSL-KDD, LDA, GA, SVM Kernels.
Hafiz Muhammad Imran and Sellappan Palaniappan are with Malaysia University of Science and Technology (MUST), Malaysia (e-mail: email@example.com). Azween Bin Abdullah is with Taylors University, Malaysia.
Cite:Hafiz Muhammad Imran, Azween Bin Abdullah, and Sellappan Palaniappan, "Towards the Low False Alarms and High Detection Rate in Intrusions Detection System," International Journal of Machine Learning and Computing vol.3, no. 4, pp. 332-336, 2013.