文章基本信息

标题：DENIAL OF SERVICE ATTACK DETECTION USING TRAPEZOIDAL FUZZY REASONING SPIKING NEURAL P SYSTEM
本地全文：下载
作者：RUFAI KAZEEM IDOWU ; RAVIE CHANDREN M. ZULAIHA ALI OTHMAN
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2015
卷号：75
期号：3
出版社：Journal of Theoretical and Applied
摘要：Although �Intrusion� is considered to be a bitter pill to swallow due to the havoc it unleashes on the cyber space, but it has become a household name to cyber-security experts because it appears to rebuff all possible solutions! Consequent upon this, there have been unrelenting efforts to reduce its negative impacts to the lowest ebb by the introduction of various Intrusion Detection Systems (IDS). Meanwhile, Spiking Neural P (SN P) system, a variant of Membrane Computing (MC), has proved to be a versatile class of distributed parallel computing model which embeds the idea of spiking neurons into P systems. Therefore, in this work, we have explored trapezoidal Fuzzy Reasoning Spiking Neural P (tFRSN P) system, which is an extension of SN P system in attack detection. Specifically, the focus is on detecting Denial-of-Service (DoS) attack with emphasis on SYN (synchronize) flood. Consequently, KDD Cup benchmark dataset was used for evaluation in series of experiments conducted. While we obtained very low False Negatives (FN) and False Positives (FP) of 0.02% and 0.25% respectively, the True Positives/Negatives were equally very high. These results have further lent credence to the fact that MC and indeed SN P system are yet-to-be tapped goldmine as far as Intrusion Detection is concerned.
关键词：SNP Systems; Attack Detection; Fuzzy Reasoning; Denial-of-Service; Membrane Computing.