Open AccessNetwork traffic detection based on part matching and section evolution of immune elements
Author(s) -
Caiming Liu,
Yan Zhang,
Cheng Xie,
Biao Wang,
Zhonghua Li
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1774/1/012071
Subject(s) - adaptability , computer science , matching (statistics) , process (computing) , anomaly detection , immune system , artificial intelligence , mathematics , ecology , statistics , immunology , biology , operating system
Immune algorithms can improve the self-adaptability for network traffic detection. Classical immune algorithms dynamically evolve and match the whole content of immune elements. However, most features of network traffic are isomeric to each other. The general matching and evolution for the whole immune elements slow down the process of self-adaptability to an extent and reduce the accuracy of immune elements’ evolution. In this paper, available network data features are analysed for the network traffic detection. The section simulation method in the immune system is studied by creating a math method for part matching of immune elements which can evolve in parts. The process of section evolution for immune elements is inferred. A detection method for recognizing anomaly network traffic is proposed. Simulation experiments show that the self-adaptability of the proposed method to the real network environment is superior to that of traditional immune algorithms.