文章基本信息

标题：Leveraging SDN for Detection and Mitigation SMTP Flood Attack through Deep Learning Analysis Techniques
本地全文：下载
作者：Mohd Zafran Abdul Aziz ; Koji Okamura
期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2017
卷号：17
期号：10
页码：166-172
出版社：International Journal of Computer Science and Network Security
摘要：This manuscript presents a mitigation of SMTP Flood attacks on SDN-based platforms. We have revisited the SMTP security issues and SDN related works to deal with the SMTP Flood attacks. We have proposed FlowIDS as a framework that can be used to detect anomaly on SMTP traffic flows. The novelty of the FlowIDS is the detection method, whereby this work has introduced a flow based attack detection of SMTP traffic flows. Decision tree (DT) classification and deep learning (DL) algorithms were used for attack metric computations and decision making. Both algorithms were tested by simulations using SDN for DT and DL . Based on the simulation results, FlowIDS has provided significant contributions in detecting and preventing SMTP flow attacks on SDN. It also provides a quick detection and mitigation capability by reducing the network bandwidth consumption since the attack traffic flows can be dropped at the early stage of attacks.
关键词：SDN; SMTP; OpenFlow; Security; ONOS; Anomaly Detection; SMTP Flood Attack; Decision Tree; Deep Learning