基于QPSO-BP的云平台信息系统安全风险分析
Security Risk Analysis of Cloud Platform Information System Based on QPSO-BP
DOI: 10.12677/MOS.2021.104097, PDF,    国家社会科学基金支持
作者: 杨志美, 潘 平:贵州大学,贵州 贵阳;潘俊宇:贵州省电子证书有限公司,贵州 贵阳
关键词: 云平台量子粒子群神经网络风险分析Cloud Platform Quantum-Behaved Particle Swarm Optimization Neural Network Risk Analysis
摘要: 云平台是云计算服务的重要载体,具有更开放、虚拟化、高度集成以及平台架构复杂等特性,更易受到各种威胁。论文在分析云平台架构及其服务模式的基础上,提出基于云平台信息系统的风险分析模型,引入量子粒子群优化BP神经网络(QPSO-BP)模型对信息系统安全风险进行分析,通过分析各风险因素对系统风险的影响,获得云平台风险因素敏感度评价,实现对风险的预测和管理。仿真表明,该方法能有效预测云平台信息系统风险,与GA-BP和PSO-BP神经网络预测方法相比有较好的网络性能和预测精度,为云平台信息系统风险管理提供一种科学有效的理论方法。
Abstract: Cloud platform is an important carrier of cloud computing services, which is more open, virtualized, highly integrated and complex in platform architecture. It is more vulnerable to various threats. Based on the analysis of cloud platform architecture and its service mode, this paper puts forward a risk analysis model based on cloud platform information system and introduces QPSO-BP model to analyze information system security risk. By analyzing the influence of various risk factors on system risk, the sensitivity evaluation of cloud platform risk factors is obtained, the risk prediction and management are realized. Simulation results show that this method can effectively predict the risk of cloud platform information system. Compared with GA-BP and PSO-BP neural network prediction methods, it has better network performance and prediction accuracy, provides a scientific and effective theoretical method for risk management of cloud platform information system.
文章引用:杨志美, 潘平, 潘俊宇. 基于QPSO-BP的云平台信息系统安全风险分析[J]. 建模与仿真, 2021, 10(4): 973-983. https://doi.org/10.12677/MOS.2021.104097

参考文献

[1] 赵波, 戴中华, 向騻. 一种云平台可信性分析模型建立方法[J]. 软件学报, 2016, 27(6): 1349-1365.
[2] 杨悦. 云平台信息安全整体保护技术探讨[J]. 中国管理信息化, 2021, 24(2): 200-201.
[3] 刘国城, 王会金. 基于AHP和熵权的信息系统审计风险评估研究与实证分析[J]. 审计研究, 2016(1): 53-59.
[4] 伍浏阳. 因子分析和支持向量机的信息系统风险评价[J]. 微电子学与计算机, 2016, 33(2): 144-148.
[5] 令狐金花, 潘平, 杜瑶瑶. 基于证据距离理论的信息系统安全风险分析[J]. 信息网络安全, 2019(9): 11-15.
[6] 王鑫, 唐作其, 许硕. 基于模糊理论和BRBPNN的信息安全风险评估[J]. 计算机仿真, 2019, 36(11): 184-189.
[7] 李森宇, 毕方明, 刘晋, 陈伟. ICS-BPNN在信息安全风险评估中的应用[J]. 中国科技论文, 2018, 13(2): 171-175.
[8] 李士勇, 李盼池. 量子计算与量子优化算法[M]. 哈尔滨: 哈尔滨工业大学出版社, 2009.
[9] 李士勇, 李盼池. 求解连续空间优化问题的量子粒子群算法[J]. 量子电子学报, 2007(5): 569-574.
[10] Sun, J. and Xu, W.B. (2004) A Global Search Strategy of Quantum-Behaved Particle Swarm Optimization. Proceedings of IEEE Conference on Cybernetics and Intel-ligent Systems, Singapore, 1-3 December 2004, 111-116.
[11] Al-Shaikhly, R. and Mazin, H. (2018) Intelligent Cloud Computing Security Using Genetic Algorithm as a Computational Tool. Journal of Physics: Conference Series, 1003, Article ID: 012024. [Google Scholar] [CrossRef
[12] 曹林, 王之腾, 陈亮, 李洪顺, 高申, 张自立. 基于改进量子免疫算法的神经网络集成[J]. 计算机工程与应用, 2020, 56(22): 142-147.
[13] 张立仿, 张喜平. 量子遗传算法优化BP神经网络的网络流量预测[J]. 计算机工程与科学, 2016, 38(1): 114-119.
[14] Stepanov, L.V., Parinov, A.V., Korotkikh, L.P. and Koltsov, A.S. (2018) Approach to Estimation of Level of Information Security at Enterprise Based on Genetic Algorithm. Journal of Physics: Conference Series, 1015, Article ID: 032141.
[15] 章恒, 禄凯. 构建云计算环境的安全检查与评估指标体系[J]. 信息网络安全, 2014(9): 115-119.