Journal on Communications ›› 2016, Vol. 37 ›› Issue (6): 119-128.doi: 10.11959/j.issn.1000-436x.2016121

• Papers • Previous Articles     Next Articles

Method for determining the lengths of protocol keywords based on maximum likelihood probability

Jian-zhen LUO1,Shun-zheng YU2,Jun CAI1   

  1. 1 School of Electronic and Information,Guangdong Polytechnic Normal University,Guangzhou 510665,China
    2 School of Information Science and Technology,Sun Yat-Sen University,Guangzhou 510006,China
  • Online:2016-06-25 Published:2017-08-04
  • Supported by:
    The National Natural Science Foundation of China;The National Natural Science Foundation of China;The Natural Science Foundation of Guangdong Province;The Natural Science Foundation of Guangdong Province;Guangdong Provincial Department of Education Innovation Project;The Excellent Young Teachers in Universities in Guangdong Province;Guangdong Provincial Application-Oriented Technical Research and Development Special;Science and Technology Planning Project of Guangdong Province;Science and Technology Major Project of Education Department of Guangdong Province;International Scientific and Technological Cooperation Projects of Education Department of Guangdong Province;Science and Technology Project of Guangdong Province

Abstract:

A left-to-right inhomogeneous cascaded hidden Markov modelwas proposed and applied to model application protocol messages.The proposed modeldescribed the transition probabilities between states and the evolution rule of phases inside the states,revealed the transition feature ofmessage fields and the left-to-right Markov characteristicsinside the fields.The protocol keywords were inferred by selecting lengths with maximum likelihood probability,and then the message format was recovered.The experimental results demonstrated that the proposed method perform well in protocol keyword extraction and message format recovery.

Key words: hidden Markov model, protocol reverse engineering, network security, message format

No Suggested Reading articles found!