A HMM-R Approach to Detect L-DDoS Attack Adaptively on SDN Controller

Wentao Wang, Xuan Ke and Lingxia Wang
Additional contact information
Wentao Wang: College of Computer Science, South-Central University for Nationalities, Wuhan 430074, China
Xuan Ke: College of Computer Science, South-Central University for Nationalities, Wuhan 430074, China
Lingxia Wang: College of Computer Science, South-Central University for Nationalities, Wuhan 430074, China

Future Internet, 2018, vol. 10, issue 9, 1-16

Abstract: A data center network is vulnerable to suffer from concealed low-rate distributed denial of service (L-DDoS) attacks because its data flow has the characteristics of data flow delay, diversity, and synchronization. Several studies have proposed addressing the detection of L-DDoS attacks, most of them are only detect L-DDoS attacks at a fixed rate. These methods cause low true positive and high false positive in detecting multi-rate L-DDoS attacks. Software defined network (SDN) is a new network architecture that can centrally control the network. We use an SDN controller to collect and analyze data packets entering the data center network and calculate the Renyi entropies base on IP of data packets, and then combine them with the hidden Markov model to get a probability model HMM-R to detect L-DDoS attacks at different rates. Compared with the four common attack detection algorithms (KNN, SVM, SOM, BP), HMM-R is superior to them in terms of the true positive rate, the false positive rate, and the adaptivity.

Keywords: L-DDoS attacks; SDN; data center network; adaptive detection; HMM-R (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2018
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/10/9/83/pdf (application/pdf)
https://www.mdpi.com/1999-5903/10/9/83/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:10:y:2018:i:9:p:83-:d:165325

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().