Information security risk prediction model based on IIWPSO-BP from perspective of alliance chain

doi:10.16265/j.cnki.issn1003-3033.2022.08.2483

Abstract

Abstract:

In order to find potential information security risks of smart cities in time, an information security risk prediction model was built based on IIWPSO algorithm optimized BP (IIWPSO-BP) neural network algorithm. Firstly, the information security risk index system was constructed by considering six aspects: information owner, shared information, alliance chain technology, information user, alliance chain management and security measures. Secondly, the information security risk prediction model was trained and tested by quantifying the information security risk index. Finally, the robustness, accuracy and time complexity of the model were compared and analyzed. The results show that the mean absolute error (MAE) of the IIWPSO-BP prediction model is 0.137 4, the mean relative error (MRE) is 0.038 5, and the fitting degree is 0.972 0. The prediction accuracy is improved by 37.6% and 65.2%, respectively, compared with the PSO-BP neural network and the BP neural network.

Key words: managementalliance chain, information security, improved inertia weight change mode particle swarm optimization(IIWPSO), back propagation (BP) neural network, risk prediction, smart city

ZHOU Xinmin, LUO Wenmin, LIU Junjie, XIE Bao. Information security risk prediction model based on IIWPSO-BP from perspective of alliance chain[J]. China Safety Science Journal, 2022, 32(8): 52-60.

Figures/Tables 8

Fig.1

Tab.1

Comparison of experimental results that meet the error threshold requirements

试验编号	隐藏层神经元数	最大迭代次数	预测值					MAE	MRE
1	6	1 000	3.912 2	3.817 9	2.403 7	1.757 3	5.110 2	0.243 8	0.081 9
2		1 100	3.703 9	4.604 8	1.864 1	1.929 8	4.594 7	0.502 5	0.144
3		2 000	3.372 9	4.538 7	2.535 5	2.303 3	5.235 7	0.433 9	0.129
4		2 100	3.407 5	3.427 2	2.171	2.129 3	5.081 7	0.441 1	0.129 7
5	7	800	3.804 3	3.794 4	3.340 6	2.030 4	4.772 9	0.199 9	0.054 9
6		2 600	2.806 9	3.551 5	2.558 2	1.819 1	5.355 7	0.524 0	0.143 8
7		3 100	3.109 3	3.480 5	2.281	1.750 6	4.882 8	0.499 2	0.148 1
8	8	300	3.680 6	4.172 1	1.993 4	2.132 7	4.154 1	0.495 3	0.138 8
9		1 000	3.619	3.84	2.634 7	1.631 3	5.077 6	0.270 5	0.091 4
10		1 700	3.161 9	4.256 9	1.951 1	2.079 2	5.138 8	0.472 4	0.138 1
11		2 000	3.851 9	3.747 3	1.821 3	2.296 1	5.180 5	0.411 2	0.135 4
12	9	200	2.634 1	3.373 2	2.756 3	1.96 3	5.108 4	0.476 4	0.123 9
13		600	4.15	4.194 2	3.233 8	2.374 1	5.445 8	0.279 6	0.088
14		1 200	3.672 1	4.047 6	2.852	1.827 5	3.558 8	0.427 4	0.103 6
15		1 600	3.783 9	3.929 1	2.949 6	2.036 1	6.064 4	0.287 6	0.063 9
16		2 000	3.649 2	4.022 3	1.998 5	2.057 5	4.485	0.389 4	0.111 8
17		2 700	3.119 6	4.264 9	2.182 7	1.819 5	4.855 8	0.457 5	0.135 6
18		2 800	2.725 1	3.862 1	3.074	1.786 1	5.182 2	0.376 6	0.104 3
19		5 000	3.308 5	4.081 3	2.543 4	1.822 7	4.959 9	0.289 4	0.088 4
20	10	200	4.266 9	4.406 9	2.235 2	2.311 2	4.807 3	0.388 5	0.123 5
21	10	1 200	3.95 4	4.836 1	1.713 9	2.003 9	5.349 2	0.504 3	0.144 2
22	11	600	2.161 6	4.036 5	2.966 2	1.965 2	6.019 3	0.592 6	0.140 3
23		1 100	4.116 6	3.724 4	2.766 1	1.98 5	4.953 9	0.137 4	0.038 6
24		1 400	3.822 6	3.393 5	2.551 8	1.404 6	5.117 3	0.389 0	0.133 3
25	12	1 000	3.646 1	4.387 1	2.867 8	2.670 3	5.479 5	0.404 6	0.132 1
26	12	1 200	3.523 1	4.033 0	2.489 9	1.683 0	5.339 2	0.335 2	0.104 8
27	13	100	4.370 1	4.442 1	2.225 5	1.547 1	4.791 0	0.449 7	0.145 9
28		400	3.846 5	4.269 4	2.244 6	2.697 8	4.960 0	0.383 2	0.142 9
29		500	3.503 1	4.185 6	2.647	2.665 8	5.303 1	0.400 9	0.136 4
30		1 100	3.407 8	3.174 5	2.784 3	1.533 4	5.265 3	0.473 1	0.142 5
31		1 400	4.006 3	3.820 6	2.669	2.307 5	5.237 3	0.212 3	0.071 6
32		2 500	3.118	4.082 1	1.974 8	2.045 1	5.061 1	0.419 1	0.123 5
33	14	100	3.862 7	5.244 1	3.513 7	1.989 6	6.010 5	0.583 2	0.114 8
34	14	3 000	3.81	3.861 5	2.475 1	1.819 8	5.735 1	0.353 7	0.098 8
35	15	700	4.12	3.147 5	3.356 3	1.685 2	4.178 3	0.493 1	0.136 7

Tab.1

Fig.2

Fig.3

Tab.2

Tab.3

Tab.4

Fig.4

References 11

[1]	石娟, 郑鹏, 常丁懿. 大数据环境下的城市公共安全治理:区块链技术赋能[J]. 中国安全科学学报, 2021, 31(2):24-32. doi: 10.16265/j.cnki.issn 1003-3033.2021.02.004
	SHI Juan, ZHENG Peng, CHANG Dingyi. Urban public security governance under big data environment: blockchain technology empowerment[J]. China Safety Science Journal, 2021, 31(2):24-32. doi: 10.16265/j.cnki.issn 1003-3033.2021.02.004
[2]	曹策俊, 李从东, 王玉, 等. 大数据时代城市公共安全风险演化与治理机制[J]. 中国安全科学学报, 2017, 27(7): 151-156. doi: 10.16265/j.cnki.issn1003-3033.2017.07.027
	CAO Cejun, LI Congdong, WANG Yu, et al. Evolution and governance mechanism of urban public safety risk in big data era[J]. China Safety Science Journal, 2017, 27(7): 151-156. doi: 10.16265/j.cnki.issn1003-3033.2017.07.027
[3]	翟伟, 盛智平, 果希光, 等. 雄安新区工程监理区块链管理模式研究与应用[J]. 中国安全科学学报, 2021, 31(4):27-33. doi: 10.16265/j.cnki.issn1003-3033.2021.04.004
	ZHAI Wei, SHENG Zhiping, GUO Xiguang, et al. Research on engineering supervision blockchain management pattern in Xiong' an new area and its application[J]. China Safety Science Journal, 2021, 31(4):27-33. doi: 10.16265/j.cnki.issn1003-3033.2021.04.004
[4]	郭祖华, 李扬波, 徐立新, 等. 面向云计算的网络安全风险预测模型的研究[J]. 计算机应用研究, 2015, 32(11):3421-3425.
	GUO Zuhua, LI Yangbo, XU Lixin, et al. Research of network security risk prediction model based on cloud computing[J]. Application Research of Computers, 2015, 32(11):3421-3425.
[5]	向尚, 邹凯, 蒋知义, 等. 基于随机森林的智慧城市信息安全风险预测[J]. 中国管理科学, 2016, 24(增1):266-270.
	XIANG Shang, ZOU Kai, JIANG Zhiyi, et al. Risk prediction of smart city information security based on random forest[J]. Chinese Journal of Management Science, 2016, 24(S1):266-270.
[6]	张艳丰, 王羽西, 邹凯, 等. 基于模糊DANP的智慧城市信息安全风险要素识别与管理策略研究[J]. 情报理论与实践, 2020, 43(10):144-150.
	ZHANG Yanfeng, WANG Yuxi, ZOU Kai, et al. Research on the identification and management strategy of risk factors of smart city information security based on fuzzy DANP[J]. Information Studies:Theory & Application, 2020, 43(10):144-150.
[7]	FRANCHINA L, SOCAL A. Innovative predictive model for smart city security risk assessment[C]. 2020 43^rd International Convention on Information, Communication and Electronic Technology (MIPRO), 2020: 1831-1836.
[8]	邹凯, 向尚, 张中青扬, 等. 智慧城市信息安全风险评估模型构建与实证研究[J]. 图书情报工作, 2016, 60(7):19-24. doi: 10.13266/j.issn.0252-3116.2016.07.003
	ZOU Kai, XIANG Shang, ZHANG Zhongqingyang, et al. Model construction and empirical study on smart city information security risk assessment[J]. Library and Information Service, 2016, 60(7):19-24.
[9]	毛子骏, 梅宏, 肖一鸣, 等. 基于贝叶斯网络的智慧城市信息安全风险评估研究[J]. 现代情报, 2020, 40(5):19-26,40.
	MAO Zijun, MEI Hong, XIAO Yiming, et al. Risk assessment of smart city information security based on Bayesian network[J]. Journal of Modern Information, 2020, 40(5):19-26,40.
[10]	腾讯电脑管家. 2018上半年区块链安全报告[EB/OL]. [2020-05-23].
[11]	中国互联网金融协会区块链研究工作组. 中国区块链金融应用与发展研究报告[EB/OL]. [2020-04-14].

样本数	IIWPSO-BP预测模型			PSO-BP预测模型			BP神经网络预测模型
	隐藏层神经元数=11 最大迭代次数=1 100			隐藏层神经元数=9 最大迭代次数=1 600			隐藏层神经元数=9 最大迭代次数=5 000
	预测值	AE	RE	预测值	AE	RE	预测值	AE	RE
1	4.116 6	0.116 6	0.029 1	3.617 9	0.382 1	-0.095 5	3.795 5	0.204 5	-0.051 1
2	3.724 4	0.275 6	-0.068 9	3.759 0	0.241 0	-0.060 2	4.005 4	0.005 4	0.001 3
3	2.766 1	0.233 9	-0.078 0	2.770 7	0.229 3	-0.076 4	3.000 3	0.000 3	0.000 1
4	1.985 0	0.015 0	-0.007 5	2.122 9	0.122 9	0.061 5	2.999 8	0.999 8	0.499 9
5	4.953 9	0.046 1	-0.009 2	5.073 3	0.073 3	0.014 7	5.000 8	0.000 8	0.000 2

隐藏层神经元数=11 最大迭代次数=1 100 IIWPSO-BP预测模型的最佳参数)
样本数	IIWPSO-BP预测模型			PSO-BP预测模型			BP神经网络预测模型
样本数	预测值	AE	RE	预测值	AE	RE	预测值	AE	RE
1	4.116 6	0.116 6	0.029 1	4.005 3	0.005 3	0.001 3	3.137 4	0.862 6	-0.215 6
2	3.724 4	0.275 6	-0.068 9	3.146 1	0.853 9	-0.213 5	3.601 4	0.398 6	-0.099 6
3	2.766 1	0.233 9	-0.078 0	2.859 0	0.141 0	-0.047 0	3.025 2	0.025 2	0.008 4
4	1.985 0	0.015 0	-0.007 5	1.643 2	0.356 8	-0.178 4	2.991 9	0.991 9	0.496 0
5	4.953 9	0.046 1	-0.009 2	4.538 5	0.461 5	-0.092 3	4.765 3	0.234 7	-0.046 9
隐藏层神经元数=9 最大迭代次数=1600 (PSO-BP预测模型的最佳参数)
样本数	IIWPSO-BP预测模型			PSO-BP预测模型			BP神经网络预测模型
样本数	预测值	AE	RE	预测值	AE	RE	预测值	AE	RE
1	3.783 9	0.216 1	-0.054	3.617 9	0.382 1	-0.095 5	3.317 9	0.682 1	-0.170 5
2	3.929 1	0.070 9	-0.017 7	3.759	0.241	-0.060 2	3.525 3	0.474 7	-0.118 7
3	2.949 6	0.050 4	-0.016 8	2.770 7	0.229 3	-0.076 4	3.223 2	0.223 2	0.074 4
4	2.036 1	0.036 1	0.018 1	2.122 9	0.122 9	0.061 5	3.232 0	1.232 0	0.616 0
5	6.064 4	1.064 4	0.212 9	5.073 3	0.073 3	0.014 7	4.517 8	0.482 2	-0.096 4
隐藏层神经元数=9 最大迭代次数=5000 (BP神经网络预测模型的最佳参数)
样本数	IIWPSO-BP预测模型			PSO-BP预测模型			BP神经网络预测模型
样本数	预测值	AE	RE	预测值	AE	RE	预测值	AE	RE
1	3.308 5	0.691 5	-0.172 9	2.961 7	1.038 3	-0.259 6	3.795 5	0.204 5	-0.051 1
2	4.081 3	0.081 3	0.020 3	3.854 3	0.145 7	-0.036 4	4.005 4	0.005 4	0.001 3
3	2.543 4	0.456 6	-0.152 2	2.667 9	0.332 1	-0.110 7	3.000 3	0.000 3	0.000 1
4	1.822 7	0.177 3	-0.088 6	1.950 7	0.049 3	-0.024 7	2.999 8	0.999 8	0.499 9
5	4.959 9	0.040 1	-0.008 0	4.793 8	0.206 2	-0.041 2	5.000 8	0.000 8	0.000 2

[1]	XIONG Xiaoxia, LIU Qingchao, SHEN Yujie, CAI Yingfeng, CHEN Long. Study on risk model of highway traffic accidents based on LSTM-BF [J]. China Safety Science Journal, 2022, 32(5): 170-176.
[2]	HE Yongbo, CAO Zhubing. Pressure compensation algorithm of fire gas sensors based on IPSO-BP model [J]. China Safety Science Journal, 2022, 32(2): 107-114.
[3]	SHI Juan, CHANG Dingyi, ZHENG Peng. An early warning model of unsafe behaviors of construction workers based on BP neural network [J]. China Safety Science Journal, 2022, 32(1): 27-33.
[4]	ZHAO Tingsheng, PANG Qizhi, JIANG Wenxi. Safety risk prediction of construction elevator based on database and SVM [J]. China Safety Science Journal, 2021, 31(4): 11-17.
[5]	LI Tingting, LU Cheng. Railway industry statistical survey system based on safety protection [J]. China Safety Science Journal, 2020, 30(S1): 133-138.
[6]	SONG Gaofeng, ZHANG Yanbing, SUN Peipei, SHEN Shuoxun, WANG Zhirong. Safety evaluation method based on acoustic emission technology for large-scale storage tanks [J]. China Safety Science Journal, 2020, 30(3): 60-66.
[7]	LI Xiang, BU Bing, ZHU Li. Research on proactive defensemethodin train control systemfor urban rail transit [J]. China Safety Science Journal, 2019, 29(S2): 62-68.
[8]	WEN Tingxin, LI Yangzi. Risk prediction model of rock burst based on preprocessing for AFOA-ELM [J]. China Safety Science Journal, 2019, 29(8): 29-34.
[9]	HAO Yongmei, DU Zhanghao, YANG Wenbin, XING Zhixiang, JIANG Juncheng, YUE Yunfei. Pipeline leakage signal identification based on improved ELMD and multi-scale entropy [J]. China Safety Science Journal, 2019, 29(8): 105-111.
[10]	XIONG Wenze, JIN Jianghong, TANG Junmei. Quantitative risk assessment method for information security of SCADA systems [J]. China Safety Science Journal, 2019, 29(8): 157-163.
[11]	SONG Bo. Safety evaluation for deep foundation pit construction in metro station based on DEA-BP neural network [J]. China Safety Science Journal, 2019, 29(5): 91-96.
[12]	FENG Zijian. Research on railway freight safety risk assessment based on BP neural network [J]. China Safety Science Journal, 2018, 28(S1): 178-185.
[13]	WEN Tingxin, YU Feng. NRS-ACPSO-SVM based model for prediction of rock burst risk [J]. China Safety Science Journal, 2017, 27(10): 19-25.
[14]	. Prediction of Coal and Gas Outburst Based on PCA-BP Neural Network [J]. China Safety Science Journal, 2013, 23(4): 45-.