基于生成对抗网络的高端装备研制数据脱敏方法

doi:10.3969/j.issn.1001-506X.2020.06.14

Abstract

Abstract:

Aiming for the confidentiality and importance of high-end equipment development data, a data hyposensitization method based on generative adversarial networks (GAN) is proposed. Considering the high-end equipment development data may face the risk of sensitive data disclosure during data mining and data sharing, the GAN for data hyposensitization is used. Experiments are carried out on randomly generated Gauss data sets. By comparing the statistical characteristics of the original data and hyposensitization data, it is proved that the data hyposensitization method based on GAN can effectively realize the data security, data utility and cost controllability. Finally, on the Yeast dataset, the desensitized data output by the GAN also performs well in real-world datasets, which can accurately predict the classification of Yeast, providing a new idea for the management and analysis of high-end equipment development data.

Key words: high-end equipment development, data hyposensitization, generative adversarial networks (GAN)

CLC Number:

TP39

Nan XIANG, Xiongtao ZHANG, Yajie DOU, Xiangqian XU, Kewei YANG, Yuejin TAN. High-end equipment development data hyposensitization method based on generative adversarial networks[J]. Systems Engineering and Electronics, 2020, 42(6): 1310-1316.

Figures/Tables 12

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Table 1

Table 2

Fig.8

Fig.9

Table 3

References 18

1	张西林, 谭跃进, 杨志伟. 多重不确定因素影响的高端装备研制任务仿真建模[J]. 系统工程与电子技术, 2018, 40 (6): 1265- 1273.
	ZHANG X L , TAN Y J , YANG Z W . Simulation modeling of high-end equipment development tasks influenced by multiple uncertain factors[J]. Systems Engineering and Electronics, 2018, 40 (6): 1265- 1273.
2	崔敏龙.商业秘密保护中数据脱敏技术研究[D].西安:西安电子科技大学, 2015.
	CUI M L. Research on data hyposensitization technology in trade secret protection[D]. Xi'an: Xidian University, 2015.
3	吴行飞.中小城市商业银行数据脱敏研究[D].济南:山东大学, 2016.
	WU X F. Research on data hyposensitization of commercial banks in small and medium cities[D]. Jinan: Shandong University, 2016.
4	乔宏明, 梁奂. 运营商面向大数据应用的数据脱敏方法探讨[J]. 移动通信, 2015, 13, 17- 20.
	QIAO H M , LIANG H . Discussion on data hyposensitization methods for operators for big data applications[J]. Mobile Communications, 2015, 13, 17- 20.
5	张嘉迅, 张传国. 网络借贷中个人信息安全保护的数据脱敏技术综述[J]. 网络安全技术与应用, 2018, 9, 73- 74.
	ZHANG J X , ZHANG C G . A survey of data hyposensitization technology for personal information security protection in internet lending[J]. Network Security Technology and Application, 2018, 9, 73- 74.
6	臧昊, 赵强, 卞水荣. 基于XML的电子病历隐私数据脱敏技术的研究与设计[J]. 信息技术与信息化, 2017, 3, 111- 114.
	ZANG H , ZHAO Q , BIAN S R . Research and design of electronic medical record privacy data hyposensitization technology based on XML[J]. Information Technology and Informatization, 2017, 3, 111- 114.
7	SARADA G, ABITHA N, MANIKANDAN G, et al. A few new approaches for data masking[C]//Proc.of the International Conference on Circuits, Power and Computing Technologies, 2015. DOI: 10.1109/ICCPCT.2015.7159301.
8	BAKKEN D E , RARAMESWARAN R , BLOUGH D M , et al. Data obfuscation: anonymity and desensitization of usable data sets[J]. IEEE Security & Privacy, 2004, 2 (6): 34- 41.
9	陈天莹, 陈剑锋. 大数据环境下的智能数据脱敏系统[J]. 通信技术, 2016, 49 (7): 915- 922. doi: 10.3969/j.issn.1002-0802.2016.07.023
	CHEN T Y , CHEN J F . Intelligent data desensitization system in big data environment[J]. Communications Technology, 2016, 49 (7): 915- 922. doi: 10.3969/j.issn.1002-0802.2016.07.023
10	GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proc.of the 27th International Conference on Neural Information Processing Systems, 2014, 2: 2672-2680.
11	刘骐宁.基于大数据的北京高端装备制造业商业模式研究[D].北京:北方工业大学, 2016.
	LIU Q N. Research on business model of Beijing high-end equipment manufacturing industry based on big data[D]. Beijing: North China University of Technology, 2016.
12	CRESWELL A , WHITE T , DUMOULIN V , et al. Generative adversarial networks: An overview[J]. IEEE Signal Processing Magazine, 2018, 35 (1): 53- 65. doi: 10.1109/MSP.2017.2765202
13	ZHANG H Y, XU S S, JIAO J T, et al. Stackelberg gan: towards prova-ble minimax equilibrium via multi-generator architectures[J]. arXiv preprint arXiv: 1811.08010, 2018.
14	NAKAI K , KANEHISA M . Expert system for predicting protein localization sites in gram-negative bacteria[J]. Proteins: Structure, Function, and Bioinformatics, 1991, 11 (2): 95- 110. doi: 10.1002/prot.340110203
15	NAKAI K , KANEHISA M . A knowledge base for predicting protein localization sites in eukaryotic cells[J]. Genomics, 1992, 14 (4): 897- 911. doi: 10.1016/S0888-7543(05)80111-9
16	BAY S D , KIBLER D , PAZZANI M J , et al. The UCI KDD archive of large data sets for data mining research and experimentation[J]. ACM SIGKDD Explorations Newsletter, 2000, 2 (2): 81- 85. doi: 10.1145/380995.381030
17	LIAW A , WIENER M . Classification and regression by random forest[J]. R news, 2002, 2 (3): 18- 22.
18	BREIMAN L . Bagging predictors[J]. Machine learning, 1996, 24 (2): 123- 140.

		平均值	标准差	最小值	25%	50%	75%	最大值
源数据	X	-0.000 6	0.702 9	-0.897 4	-0.858 8	-0.000 1	0.858 6	0.904 5
源数据	Y	-0.001 8	0.711 5	-1.034 2	-0.506 8	-0.472 7	0.507 2	1.033 8
生成数据	X	-0.000 6	0.704 5	-0.885 8	-0.857 8	-0.000 6	0.856 8	0.894 7
生成数据	Y	0.008 5	0.705 9	-1.000 0	-0.487 5	-0.461 8	0.512 4	1.000 0

	层	输入	输出	激活函数
生成器	Liner	Dim	32	BatchNorm1d
生成器	Liner	32	Dim	LeakyRelu
判别器	Liner	2	512	LeakyRelu
	Liner	512	256	LeakyRelu
	Liner	256	1	Sigmoid

	精确度	召回率	F1分数	支持数
类别1	0.96	0.97	0.96	255
类别2	0.72	0.62	0.67	29
精确度			0.94	284
宏平均值	0.84	0.80	0.82	284
加权平均值	0.93	0.94	0.93	284

[1]	Pengyu CAO, Chengzhi YANG, Limeng SHI, Hongchao WU. LPI radar signal enhancement based on DAE-GAN network [J]. Systems Engineering and Electronics, 2021, 43(9): 2493-2500.
[2]	Fan ZHAO, Hu JIN. Communication jamming waveform generation technology based on GAN [J]. Systems Engineering and Electronics, 2021, 43(4): 1080-1088.
[3]	Xiaojing YIN, Xiaofeng HU, Rongxiang LIU, Zhige XIE, Jun MA. Generative method of SOS capability maps based on GAN [J]. Systems Engineering and Electronics, 2020, 42(10): 2257-2264.
[4]	ZHANG Xilin, TAN Yuejin, YANG Zhiwei. Simulation modeling of high-end equipment development task influenced by multiple uncertainty factors [J]. Systems Engineering and Electronics, 2018, 40(6): 1265-1273.

High-end equipment development data hyposensitization method based on generative adversarial networks

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 18

Related Articles 4

Recommended Articles

Metrics

Comments