Blind identification of network protocols based on improved Apriori algorithm. Issue 1 (January 2020)

• Record Type: Journal Article
• Authors: Chen, Yingchun; Dai, Yuchen; Xue, Jingliang; Dong, Fang
• Is Part Of: IOP conference series. Volume 740:Issue 1(2020)
• Publication Date: 2020-01
• Subjects: Materials science -- Periodicals; 620.1105
• DOI: 10.1088/1757-899X/740/1/012040
• Languages: English
• ISSNs: 1757-8981

Abstract

Abstract: With the development and application of network technology and private protocols, more and more unknown protocols are found in communication networks. Analysis and identification of unknown protocols has become an important and difficult problem in obtaining valuable information from data. Based on the traditional Apriori algorithm, a reduced bit string algorithm and a weight compression algorithm are proposed to identify the unknown protocols according to the characteristics of network unknown protocol data in this paper. These proposed algorithms make use of location information, matrix compression, bit string and weight compression to gradually improve the identification accuracy and the processing efficiency of unknown protocols. Experiments on simulation data and actual data demonstrate the performance of the improved algorithms in terms of identification accuracy and time efficiency.