Research Article
Intrusion Detection System using Log Files and Reinforcement Learning
|
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
| Volume 45 - Issue 19 |
| Published: May 2012 |
| Authors: Bhagyashree Deokar, Ambarish Hazarnis |
10.5120/7026-9675
|
Bhagyashree Deokar, Ambarish Hazarnis . Intrusion Detection System using Log Files and Reinforcement Learning. International Journal of Computer Applications. 45, 19 (May 2012), 28-35. DOI=10.5120/7026-9675
@article{ 10.5120/7026-9675,
author = { Bhagyashree Deokar,Ambarish Hazarnis },
title = { Intrusion Detection System using Log Files and Reinforcement Learning },
journal = { International Journal of Computer Applications },
year = { 2012 },
volume = { 45 },
number = { 19 },
pages = { 28-35 },
doi = { 10.5120/7026-9675 },
publisher = { Foundation of Computer Science (FCS), NY, USA }
}
%0 Journal Article
%D 2012
%A Bhagyashree Deokar
%A Ambarish Hazarnis
%T Intrusion Detection System using Log Files and Reinforcement Learning%T
%J International Journal of Computer Applications
%V 45
%N 19
%P 28-35
%R 10.5120/7026-9675
%I Foundation of Computer Science (FCS), NY, USA
Abstract
World Wide Web is widely accessed by people for accessing services, social networking and so on. All these activities of users are traced in different types of log files. Hence, log files prove to be extremely useful in understanding user behavior, improving server performance, improving cache replacement policy, intrusion detection, etc. In this paper, we focus on the intrusion detection application of log files. By analyzing drawbacks and advantages of existing intrusion detection techniques, the paper proposes an intrusion detection system that attempts to minimize drawbacks of existing intrusion detection techniques, viz. false alarm rate and inability to detect unknown attacks. To accomplish this, association rule learning, reinforcement learning and log correlation techniques have been used collaboratively
References
- Tesink, S. (2007). Improving Intrusion Detection Systems through Machine Learning. Group, (07).
- Cramer, M. L. , Cannady, J. , & Harrell, J. (1996). New Methods of Intrusion Detection using Control-Loop Measurement. Information Systems Security, 1-10.
- Abad, C. , Taylor, J. , & Rowe, K. (n. d. ). Log Correlation for Intrusion Detection?: A Proof of Concept Systems Research.
- Paper, W. (n. d. ). Firewalls – Overview and Best Practices. Information Systems.
- Kerkhofs, J. , &Pannemans, D. (2001). Web Usage Mining on Proxy Servers?: A Case Study.
- Ning, P. , & Carolina, N. (n. d. ). Intrusion Detection Techniques. Bernoulli.
- Booth, D. , & Jansen, B. J. (n. d. ). A Review of Methodologies for Analyzing Websites, 141-162.
- Zhang, C. , Zhang, G. , & Sun, S. (2009). A Mixed Unsupervised Clustering-Based Intrusion Detection Model. 2009 Third International Conference on Genetic and Evolutionary Computing, 426-428. Ieee. doi:10. 1109/WGEC. 2009. 72
- Salama, S. E. , I. Marie, M. , El-Fangary, L. M. , & K. Helmy, Y. (2011). Web Server Logs Preprocessing for Web Intrusion Detection. Computer and Information Science, 4(4), 123-133. doi:10. 5539/cis. v4n4p123
- Brugger, S. T. (n. d. ). Data Mining Methods for Network Intrusion Detection, V, 1-35.
Index Terms
Keywords