An association analysis and identification for unknown protocol of bitstream oriented

摘要

As for the bitstream data features in mobile wireless network, a method based on association rules was proposed to identify the unknown protocol in certain circumstances. The method improved traditional protocol identification technology to reduce its limitation by ways of port number and fixed features of known protocol. Through capturing bitstream data transmitted in wireless environment, the method extracted the feature information and also mined the association rules to identify and mark the unknown protocol using the learning mechanism of machine. Then the unknown protocol in a specific environment was found and analyzed by marking the fingerprint information of protocol. Finally, the efficiency of the method was evaluated by two kinds of protocol to obtain that the average recognition rate of protocol was more than 99%, while the average false-recognition rate is less than 0.6%. Copyright © 2016 John Wiley & Sons, Ltd.