THE ANALYSIS OF USER BEHAVIOUR IN WEB APPLICATIONS AND NETWORK SECURITY

Abstract

Nowadays, more and more online services, including web pages, as well as some client applications which are based on web services, security problems based on web applications become more serious. Most intrusion detection systems are based on every single request to find the cyber-attack instead of users’ behaviors. In order to detect newly developed attacks, the system analyze web logs from web servers and define users’ behaviors to divide them into normal and malicious ones. Anomaly detection method of user behavior is used to detect the internal attackers of database system. With using Discrete-time Markov Chains (DTMC), an anomaly detection system of user behavior is already proposed, which can detect the internal threats of database system. The experimental results show that this detection system can detect normal and abnormal user behavior precisely and effectively. These Previous research propose a novel method of user behavior analysis in semantic network. Using the weight value to analyze and record user behavior and then check user behavior record with the signatures which are generated by the Intrusion Detection System (IDS). Fuzzy expert system enables it to identify user behaviors and categorize suspicious behaviors with various levels of intensity. The method proposed in this paper is “Network Security Based On The Analysis Of user Behaviour For Web Applications”. This proposed methodology gives an attention on Web usage mining to predict the behavior of web users based on web server log files.