The Assessment Method of Network Security Situation Based on Improved BP Neural Network
With the popularity of the Internet and the emergence of cloud computing, network security issues have become increasingly prominent. In view of the low efficiency and poor reliability of the existing network security situation assessment methods, this paper proposes a quantitative assessment method based on an improved BP neural network. Aiming at the disadvantages of slow convergence speed, easy oscillation, and local minimum in BP neural network, this paper optimized the algorithm by combining Cuckoo search algorithm, introducing momentum factor and adaptive learning rate. The simulation results show that the improved CS-BPNN algorithm in this paper has fast convergence rate and high evaluation accuracy, which provides a new method for network situation assessment.
KeywordsNetwork security situation assessment BP neural network Cuckoo search algorithm Momentum factor
- 1.Bian, N., Wang, X., Mao, L.: Network security situational assessment model based on improved AHP_FCE. In: International Conference on Advanced Computational Intelligence, pp. 200–205. IEEE (2013)Google Scholar
- 2.Han, M.N., Liu, Y., Chen, Y.: Network security situational awareness model based on set pair analysis. Appl. Res. Comput. 29(10), 3824–3827 (2012)Google Scholar
- 3.Liu, Z., Zhang, B., Zhu, N., Li, L.: Hierarchical network threat situation assessment method for DDoS based on D-S evidence theory. In: IEEE International Conference on Intelligence and Security Informatics, pp. 49–53. IEEE (2017)Google Scholar
- 5.Xiao, P., Xian, M., Wang, H: Network security situation prediction method based on MEA-BP. In: International Conference on Computational Intelligence & Communication Technology, pp. 1–5. IEEE (2017)Google Scholar
- 6.Chen, G., Zhao, Y.Q.: RF-SVM based awareness algorithm in intelligent network security situation awareness system. In: The Workshop on Advanced Research & Technology in Industry (2017)Google Scholar