Journal Article

ANOMALY DETECTION ON USER BROWSING BEHAVIORS FOR PREVENTION APP_DDOS

Devale, Prakash, Jadhav, Vidya

2011

Overview

Some of the hardest to mitigate distributed denial of service attacks (DDoS) are ones targeting the application layer. Over the time, researchers proposed many solutions to prevent denial of service attacks (DDoS) from IP and TCP layers instead of the application layer. New application Layer based DDoS attacks utilizing legitimate HTTP requests to overwhelm victim resources are more undetectable. This may be more serious when such attacks mimic or occur during the flash crowd event of the website. This paper present a new application layer anomaly detection and filtering based on Web user browsing behavior for create defense against Distributed Denial of Service Attack(DDoS). Based on hyperlink characteristics such as request sequences of web pages. This paper, uses a large scale Hidden Semi Markov Model (HsMM) to describe the web access behavior and online implementation of model based observation sequence on user browsing behavior fitting to the model measure of user's normality.

• Publisher: I A E T Publishing Company
• Subject: Anomalies / Browsing / Denial of service attacks / Filtering / Mathematical models / On-line systems / TCP (protocol) / Websites