Intrusion Detection using Machine Learning and log analysis

Abstract: Web-based applications has gained universal acceptance in every field of lives, including social, commercial, government, and academic communities. Even with the recent emergence of technology, most of applications are accessed and controlled through web interfaces this work proposes a multistage log analysis architecture, which combines both pattern matching and machine learning methods. It makes use of logs generated by the application during attacks to effectively detect attacks and to help preventing future attacks. The architecture is explained in detail with a proof-of-concept prototype is implemented using pattern matching and Bayes Net for machine learning. Experiment outcomes show that the two-stage system has combined the advantages of both systems, and has improved the detection accuracy. The proposed work is significant in advancing web securities, while the multi-stage log analysis concept would be highly applicable to many intrusion detection applications. In proposed system we are use Intrusion detection technology on net banking application to detect various types of attack that affect net banking application.

Keywords: SQL injection, Machine Learning, Web Security