Distributed Denial of Service Attack Detection Using Wallaroo-Based Time-Series Analysis
Farzana Zakaria1, Mohd Fadzil Abdul Kadir2, Mohamad Afendee Mohamed3, Ahmad Faisal Amri Abidin4, Ahmad Nazari Mohd Rose5
1Farzana Zakaria, Faculty of Informatics and Computing, Universiti Sultan Zainal Abidin, Terengganu, Malaysia.
2Mohd Fadzil Abdul Kadir, Faculty of Informatics and Computing, Universiti Sultan Zainal Abidin, Terengganu, Malaysia.
3Mohamad Afendee Mohamed, Faculty of Informatics and Computing, Universiti Sultan Zainal Abidin, Terengganu, Malaysia.
4Ahmad Faisal Amri Abidin, Faculty of Informatics and Computing, Universiti Sultan Zainal Abidin, Terengganu, Malaysia.
5Ahmad Nazari Mohd Rose, Faculty of Informatics and Computing, Universiti Sultan Zainal Abidin, Terengganu, Malaysia.
Manuscript received on 16 February 2019 | Revised Manuscript received on 07 March 2019 | Manuscript Published on 08 June 2019 | PP: 634-637 | Volume-7 Issue-5S4, February 2019 | Retrieval Number: E11320275S419/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Nowadays, with the growth of computer technologies, there had been many problems arise regarding security issues. The hackers tend to try to break into any website they desired and affect it either by modified, steal information or shutdown the server. Distributed Denial of Service (DDoS) attacks falls into one of the category of critical at-tacks. DDoS attacks can be described as temporarily deny several services of the end users. In general, it usually consumes network resources and overloads the system with undesired request. Thus, the network can be protected against such attacks using an Intrusion Detection System. This paper presents the method of detecting DDoS attacks by using the Wallaroo-based by analyzing the change of the time series data obtained from the weighted mean and weighed standard deviation of data. Wallaroo-based is about the distributed data processing framework for building high-performance streaming data applications. A streaming DDoS attack detector is constructed, which consumes a stream of request logs from a large group of servers and uses statistical anomaly detection to alert user when a server is under attack.
Keywords: Distributed Denial of Service, Time-Series Analysis, Intrusion Detection System, Wallaroo.
Scope of the Article: Real-Time Information Systems