An intelligent trust model for hybrid DDoS detection in software defined networks. (2nd May 2019)

• Record Type: Journal Article
• Authors: Gong, Changqing; Yu, Delong; Zhao, Liang; Li, Xiguang; Li, Xianwei
• Other Names: Wu Yulei guestEditor.; Yan Zheng guestEditor.; Zhao Zhiwei guestEditor.; Al‐Dubai Ahmed guestEditor.; Li Tonglin guestEditor.; Xie Bing guestEditor.; Zhang Boyu guestEditor.
• Is Part Of: Concurrency and computation. Volume 32:Number 16(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-05-02
• Subjects: hybrid DDoS -- intelligent trust model -- software defined networks; Parallel processing (Electronic computers) -- Periodicals; Parallel computers -- Periodicals; 004.35
• DOI: 10.1002/cpe.5264
• Languages: English
• ISSNs: 1532-0626

Abstract

Summary: Software Defined Networks (SDNs) have been extensively studied in recent years. The centralised and programmable controller also brings many security challenges. As a conventional attack with the purpose of destruction, Distributed Denial of Service (DDoS) is still a threat for Software Defined Networks (SDNs). There is a lack of trust evaluation and management mechanism between the OpenFlow switches in SDNs. Therefore, in this paper, we propose a trust evaluation and management model, namely, the Intelligent Trust Model (ITM). In this framework, the Extreme Learning Machine (ELM) is applied to detect hybrid DDoS in Software Definition Networks (SDNs). Our model (ITM) can update the trust value of the OpenFlow switches in real time and respond quickly to different types of DDoS attacks. Compared with others, the experiment results show that our model can provide more efficient detection with high detection accuracy and low false positive rate for the hybrid DDoS attack. At last, in our proposal, OpenFlow switches with higher trust have a relatively higher priority. Therefore, we solve the flow conflict issue in the infrastructure layer.