An Entropy-SVM Based Interest Flooding Attack Detection Method in ICN
Ting Zhi, Ying Liu, Zhiwei Yan · 2018
As an instantiation of Information-centric Networking (ICN), Named Data Networking (NDN) was proposed. Since the Interests are recorded in the PITs of the intermediate routers until they receive corresponding Data packets or exceed the expiring time, the attackers can send excessive number of spoofed Interests to occupy the PITs, which is called Interest Flooding Attack (IFA), to degrade the network performance. In this paper, we propose an IFA detection mechanism based on Support Vector Machine (SVM), which can detect the IFA effectively. In order to improve the accuracy of the attack detection, we use the information entropy of the Interest names, the usage of PIT and the satisfaction rate of the Interests as the extracted features in the SVM classifier. In addition, we evaluate the performance of our mechanism. The simulation results validate that the mechanism can accurately and effectively detect the IFA.