A new traffic pattern matching for DDoS traceback using independent component analysis

Yuji Waizumi, Tohru Sato, Yoshiaki Nemoto

Research output: Contribution to journalArticlepeer-review


Recently, Denial of Service(DoS) attacks and Distributed DoS(DDoS) attacks which are stronger form of DoS attacks important to identify the attack source and to block attack traffic as from plural hosts have become security threats on the Internet. It is one of the measures against these attacks. In general, it is difficult to identify them because information about the attack source is falsified. Therefore a method of identifying the attack source by tracing the route of the attack traffic is necessary. A traceback method which uses traffic patterns, using changes in the number of packets over time as criteria for the attack traceback has been proposed. The traceback method using the traffic patterns can trace the attack by matching the shapes of input traffic patterns and the shape of output traffic pattern observed at a network branch point such as a router. The traffic pattern is a shapes of traffic and unfalsifiable information. The proposed trace methods proposed till date cannot obtain enough tracing accuracy, because they directly use traffic patterns which are influenced by non-attack traffics. In this paper, a new traffic pattern matching method using Independent Component Analysis(ICA) is proposed.

Original languageEnglish
Pages (from-to)760-766
Number of pages7
JournalWorld Academy of Science, Engineering and Technology
Publication statusPublished - 2011 Dec


  • Distributed denial of service
  • Independent component analysis
  • Traffic pattern

ASJC Scopus subject areas

  • Engineering(all)


Dive into the research topics of 'A new traffic pattern matching for DDoS traceback using independent component analysis'. Together they form a unique fingerprint.

Cite this