Publication detail

Evolutionary Circuit Design for Fast FPGA-Based Classification of Network Application Protocols

GROCHOL, D. SEKANINA, L. KOŘENEK, J. ŽÁDNÍK, M. KOŠAŘ, V.

Original Title

Evolutionary Circuit Design for Fast FPGA-Based Classification of Network Application Protocols

Type

journal article in Web of Science

Language

English

Original Abstract

The evolutionary design can produce fast and efficient implementations of digital circuits. It is shown in this paper how evolved circuits, optimized for the latency and area, can increase the throughput of a manually designed classifier of application protocols. The classifier is intended for high speed networks operating at 100 Gbps. Because a very low latency is the main design constraint, the classifier is constructed as a combinational circuit in a field programmable gate array (FPGA). The classification is performed using the first packet carrying the application payload. The improvements in latency (and area) obtained by Cartesian genetic programming are validated using a professional FPGA design tool. The quality of classification is evaluated by means of real network data. All results are compared with commonly used classifiers based on regular expressions describing application protocols.

Keywords

Application protocol, Classifier, Cartesian genetic programming, Field programmable gate array

Authors

GROCHOL, D.; SEKANINA, L.; KOŘENEK, J.; ŽÁDNÍK, M.; KOŠAŘ, V.

Released

1. 1. 2016

ISBN

1568-4946

Periodical

APPLIED SOFT COMPUTING

Year of study

38

Number

1

State

Kingdom of the Netherlands

Pages from

933

Pages to

941

Pages count

9

URL

https://www.fit.vut.cz/research/publication/10900/

BibTex

@article{BUT130909,
  author="David {Grochol} and Lukáš {Sekanina} and Jan {Kořenek} and Martin {Žádník} and Vlastimil {Košař}",
  title="Evolutionary Circuit Design for Fast FPGA-Based Classification of Network Application Protocols",
  journal="APPLIED SOFT COMPUTING",
  year="2016",
  volume="38",
  number="1",
  pages="933--941",
  doi="10.1016/j.asoc.2015.09.046",
  issn="1568-4946",
  url="https://www.fit.vut.cz/research/publication/10900/"
}

Documents

gro-asc16final.pdf