Building an intrusion detection system based on support vector machine and genetic algorithm

Authors:
Rongchang Chen;Jeanne Chen;Tungshou Chen;Chunhung Hsieh;Teyu Chen;Kaiyang Wu
Affiliations:
Department of Logistics Engineering and Management, National Taichung Institute of Technology;Department of Computer Science and Information Management, Hungkuang University, Taichung, Taiwan, China;Department of Information Management, National Taichung Institute of Technology, Taichung, Taiwan, China;Department of Information Management, National Taichung Institute of Technology, Taichung, Taiwan, China;Department of Information Management, Hsiuping Institute of Technology, Taichung, Taiwan, China;Department of Information Management, National Taichung Institute of Technology, Taichung, Taiwan, China
Venue:
ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part III
Year:
2005

Citing 7
Cited 3

An Intrusion-Detection Model

IEEE Transactions on Software Engineering - Special issue on computer security and privacy
Machine Learning and Data Mining; Methods and Applications

Machine Learning and Data Mining; Methods and Applications
Genetic Algorithms: Concepts and Designs with Disk

Genetic Algorithms: Concepts and Designs with Disk
TCP/IP Protocol Suite

TCP/IP Protocol Suite
Automated discovery of concise predictive rules for intrusion detection

Journal of Systems and Software
Building agents for rule-based intrusion detection system

Computer Communications
A comparison of methods for multiclass support vector machines

IEEE Transactions on Neural Networks

A new parameter-free classification algorithm based on nearest neighbor rule and K-means for mobile devices

ACOS'07 Proceedings of the 6th Conference on WSEAS International Conference on Applied Computer Science - Volume 6
Application of support vector machines on prediction of repeat visitation

CIMMACS'06 Proceedings of the 5th WSEAS International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics
A new binary classifier: clustering-launched classification

ICIC'06 Proceedings of the 2006 international conference on Intelligent computing: Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Host-based Intrusion Detection System (IDS) utilizes the log files as the data source and is limited by the content of the log files. If the log files were tampered, the IDS cannot accurately detect illegal behaviors. Therefore, the proposed IDS for this paper will create its own data source file. The system is controlled by the Client program and Server program. The client program is responsible for recording a user's behavior in the data source file. The data source file is then transmitted to the server program, which will send it to SVM to be analyzed. The analyzed result will then be transmitted back to the client program. The client program will then decide on the course of actions to take based on the analyzed result. Also, the genetic algorithm is used to optimize information to extract from the data source file so that detection time can be optimized.