Title: Retrieval method for multi-level network malicious intrusion information based on sequential logic model

Authors: A-jun Cui; Yan-hong Ma; Chen Li; Xiao-ming Wang

Addresses: College of Electronical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China; State Grid Gansu Electric Power Company, Lanzhou 730050, China ' State Grid Gansu Electric Power Company, Lanzhou 730050, China ' College of Foreign Languages, Lanzhou University of Technology, Lanzhou 730050, China ' College of Electronical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China

Abstract: In order to improve the security of multi-level networks, a retrieval method for multi-level network malicious intrusion information based on sequential logic model is proposed. In this method, a big data analysis model for retrieval of multi-level network malicious intrusion information is established. The fusion tracking clustering analysis method is adopted to establish a feature matching function of balanced scheduling parameters, and the fuzzy feature matching is adopted to realise information feature clustering. The sequential logic model is introduced to analyse the discrete parameters of information features, and a model for extracting parameter features of malicious intrusion information is constructed. With auto-correlation feature matching, retrieval and intelligent recognition of malicious intrusion information is realised. The simulation results show that this method consumes less time in retrieval of multi-level network malicious intrusion information (within 2 ms), with a high accuracy (average accuracy of 96.35%).

Keywords: sequential logic model; multi-level network; malicious intrusion; information retrieval; network security.

DOI: 10.1504/IJICT.2022.126489

International Journal of Information and Communication Technology, 2022 Vol.21 No.4, pp.386 - 397

Received: 23 Oct 2020
Accepted: 13 Dec 2020
Published online: 26 Oct 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article