计算机工程与应用 ›› 2022, Vol. 58 ›› Issue (11): 117-124.DOI: 10.3778/j.issn.1002-8331.2110-0391

• 网络、通信与安全 • 上一篇    下一篇

基于SAA-SSA-BPNN的网络安全态势评估模型

张然,潘芷涵,尹毅峰,蔡增玉   

  1. 郑州轻工业大学 计算机与通信工程学院,郑州 450000
  • 出版日期:2022-06-01 发布日期:2022-06-01

Network Security Situation Assessment Model Based on SAA-SSA-BPNN

ZHANG Ran, PAN Zhihan, YIN Yifeng, CAI Zengyu   

  1. College of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450000, China
  • Online:2022-06-01 Published:2022-06-01

摘要: 针对目前网络安全态势评估模型准确性和收敛性有待提高的问题,提出一种基于SAA-SSA-BPNN的网络安全态势评估模型。该模型利用模拟退火算法(SAA)可以一定概率接受劣解并有大概率跳出局部极值达到全局最优解的特性来优化麻雀搜索算法,利用优化后的麻雀搜索算法(SSA)具有良好稳定性和收敛速度快且不易陷入局部最优的特点对BP神经网络(BPNN)进行改进,找到最佳适应度个体并获取最优权值和阈值,将其作为初始值赋给BP神经网络,将预处理后的指标数据输入改进后的BP神经网络模型对其进行训练,利用训练好的模型对网络系统所遭受威胁的程度进行评估。对比实验结果表明,该评估模型比其他基于改进BP神经网络的态势评估模型准确性更高,收敛速度更快。

关键词: 网络安全, 态势评估, BP神经网络, 模拟退火算法, 麻雀搜索算法

Abstract: To solve the problems that the accuracy and convergence of current network security situation assessment models need to be improved, a network security situation assessment model based on SAA-SSA-BPNN is proposed. In this model, the sparrow search algorithm(SSA) is optimized by the simulated annealing algorithm(SAA) that can accept the inferior solution with a certain probability and jump out of the local extreme value with a high probability to reach the global optimal solution, and the BP neural network(BPNN) is improved by the optimized sparrow search algorithm that has good stability, fast convergence speed and is not easy to fall into the local optimum, so as to find the best fitness individual, and obtain the optimal weight and threshold, then assign them to the BP neural network as the initial values. The preprocessed index data is input into the improved BP neural network model for training, and finally the threat degree of the network system is assessed based on the trained model. Comparative experimental results show that this assessment model has higher accuracy and faster convergence than other situation assessment models based on improved BP neural network.

Key words: network security, situation assessment, back propagation(BP) neural network, simulated annealing algorithm, sparrow search algorithm