Research on network security situation evaluation based on multivariate linear regression model

Yutong Guo; Boyuan Fu; Yukun Zhang

doi:10.54097/w8z42p17

Authors

Yutong Guo
Boyuan Fu
Yukun Zhang

DOI:

https://doi.org/10.54097/w8z42p17

Keywords:

network security, comparative analysis, factor, Multivariate regression analysis, policy, optimization.

Abstract

Technology development facilitates life, but frequent cybersecurity incidents have caused complex jurisdiction across borders. In order to solve the problem of policy effectiveness and the distribution of cybercrime, the comparison of national policies and crimes and the impact of demographic characteristics on the distribution of crimes is analyzed. This paper adopts multiple linear regression, double differential method (DiD) and stepwise regression analysis model, and combines ITU crime data for comparison and analysis; regression analysis and its visualization methods are used, including scatter plots, contrast line plots, etc., to explore demographic data. With cybercrime impact and successfully predict future crime events. The study found that national policy differences significantly affect the incidence and success rates of cybercrime. Effective implementation of policies can curb crime and improve judicial efficiency. In addition, increased Internet access rates, uneven wealth and low education levels have all aggravated cybercrime. Improving education and cybersecurity awareness is crucial to preventing and responding to cybercrime. To sum up, this study provides valuable reference for governments to formulate and optimize cybersecurity policies, and also provides solid theoretical basis and practical guidance for preventing and responding to cybercrime.

Downloads

Download data is not yet available.

References

[1] Wall D S. Cybercrime: The transformation of crime in the information age [M]. John Wiley & Sons, 2024.

[2] Sarker I H, Kayes A S M, Badsha S, et al. Cybersecurity data science: an overview from machine learning perspective [J]. Journal of Big data, 2020, 7: 1 - 29.

[3] Sarker I H, Abushark Y B, Alsolami F, et al. Intrudtree: a machine learning based cyber security intrusion detection model [J]. Symmetry, 2020, 12 (5): 754.

[4] Eschmann J. Reward function design in reinforcement learning [J]. Reinforcement learning algorithms: Analysis and Applications, 2021: 25 - 33.

[5] Barbu A, Zhu S C. Monte carlo methods [M]. Singapore: Springer Singapore, 2020.

[6] Icarte R T, Klassen T Q, Valenzano R, et al. Reward machines: Exploiting reward function structure in reinforcement learning [J]. Journal of Artificial Intelligence Research, 2022, 73: 173 - 208.

[7] Shakya A K, Pillai G, Chakrabarty S. Reinforcement learning algorithms: A brief survey [J]. Expert Systems with Applications, 2023, 231: 120495.

[8] Haim N, Vardi G, Yehudai G, et al. Reconstructing training data from trained neural networks [J]. Advances in Neural Information Processing Systems, 2022, 35: 22911 - 22924.

[9] Sarker IH, Salim FD. Mining user behavioral rules from smartphone data through association analysis. In: Proceedings of the 22nd Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), Melbourne, Australia. New York: Springer; 2018. p. 450 – 61.

[10] Liao H-J, Lin C-HR, Lin Y-C, Tung K-Y. Intrusion detection system: a comprehensive review. J Netw Comput Appl. 2013; 36 (1): 16 – 2.