Botnet detection used fast-flux technique, based on adaptive dynamic evolving spiking neural network algorithm. (28th January 2021)

• Record Type: Journal Article
• Authors: Almomani, Ammar; Al-Nawasrah, Ahmad; Alauthman, Mohammad; Al-Betar, Mohammed Azmi; Meziane, Farid
• Is Part Of: International journal of ad hoc and ubiquitous computing. Volume 36:Number 1(2021)
• Page Start: 50
• Page End: 65
• Publication Date: 2021-01-28
• Subjects: dynamic evolving spiking neural network -- fast-flux techniques detection -- network security -- botnet; Ubiquitous computing -- Periodicals; Embedded computer systems -- Periodicals; Electronic data processing -- Distributed processing -- Periodicals; Wireless communication systems -- Periodicals; Computer architecture -- Periodicals; 004.2
• Languages: English
• ISSNs: 1743-8225

Abstract

A botnet refers to a group of machines. These machines are controlled distantly by a specific attacker. It represents a threat facing the web and data security. Fast-flux service network (FFSN) has been engaged by bot herders for cover malicious botnet activities. It has been engaged by bot herders for increasing the lifetime of malicious servers through changing the IP addresses of the domain name quickly. In the present research, we aimed to propose a new system. This system is named fast flux botnet catcher system (FFBCS). This system can detect FF-domains in an online mode using an adaptive dynamic evolving spiking neural network algorithm. Comparing with two other related approaches the proposed system shows a high level of detection accuracy, low false positive and negative rates, respectively. It shows a high performance. The algorithm's proposed adaptation increased the accuracy of the detection. For instance, this accuracy reached (98.76%) approximately.