MCDP:基于神经网络的多集群分布式差分隐私数据发布方法

doi:10.3969/j.issn.0372-2112.2020.12.002

电子学报 ›› 2020, Vol. 48 ›› Issue (12): 2297-2303.DOI: 10.3969/j.issn.0372-2112.2020.12.002

MCDP:基于神经网络的多集群分布式差分隐私数据发布方法

陈思^1,2, 付安民¹, 柯海峰¹, 苏铓¹, 孙怀江¹

1. 南京理工大学计算机科学与工程学院, 江苏南京 210094;
2. 南京理工大学信息化建设与管理处, 江苏南京 210094

收稿日期:2019-09-23 修回日期:2019-12-15 出版日期:2020-12-25
- 通讯作者:
- 付安民
- 作者简介:
- 陈思女,1987年生于湖北襄阳.现为南京理工大学计算机科学与工程学院博士研究生.主要研究方向为大数据隐私保护.E-mail:chensi@njust.edu.cn;柯海峰 男,1993年生于湖北鄂州.南京理工大学计算机科学与工程学院硕士研究生.主要研究方向为隐私保护.E-mail:14700533@qq.com;苏铓女,1987年生于内蒙古翁牛特旗.现为南京理工大学计算机科学与工程学院副教授.主要研究方向为云安全、访问控制与权限管理.E-mail:sumang@njust.edu.cn;孙怀江 男,1968年生于陕西西安.现为南京理工大学计算机科学与工程学院教授、博士生导师.主要研究方向为神经网络与机器学习.E-mail:sunhuaijiang@njust.edu.cn
- 基金资助:
- 国家自然科学基金 (No.61572255，No.61702266）; 江苏省"六大人才高峰"高层次人才基金资助项目 (No.XYDXXJS-032）; 赛尔网络下一代互联网技术创新项目 (No.NGII20190804，No.NGII20150117）

MCDP:Multi-Cluster Differential Privacy Data Publishing Method Based on Neural Network

CHEN Si^1,2, FU An-min¹, KE Hai-feng¹, SU Mang¹, SUN Huai-jiang¹

1. School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu 210094, China;
2. Division of Information Construction and Management, Nanjing University of Science and Technology, Nanjing, Jiangsu 210094, China

Received:2019-09-23 Revised:2019-12-15 Online:2020-12-25 Published:2020-12-25
- Corresponding author:
- FU An-min
- Supported by:
- National Natural Science Foundation of China (No.61572255, No.61702266); High Level Talent Program of Six Talents Peaks in Jiangsu Province (No.XYDXXJS-032); CERNET Innovation Project (No.NGII20190804, No.NGII20150117)

摘要/Abstract

摘要： 大数据应用能够为人们的生活和工作方式提供便捷，但包含消费记录、社交关系、地理位置等个人隐私信息的数据在发布过程中可能被服务提供商收集，用户隐私面临巨大威胁.本文首次提出了一个基于神经网络的多集群分布式差分隐私数据发布方法，能够显著缓解单服务器的数据处理压力.同时，利用神经网络算法进行隐私参数预测明显提高了预测精度和预测效率，并且集群之间不同的隐私参数也保证了方案的灵活性.此外，由于中心服务器存储的是经过差分隐私处理后的统计数据，即使中心服务器由于遭受攻击导致存储的数据泄露，也能确保用户数据隐私.实验对比分析表明，我们的方法在隐私处理效率、隐私保护强度、预测精度和预测效率等方面都有明显优势.

关键词: 数据发布, 差分隐私, 服务协同, 神经网络, 多集群, 分布式

Abstract: Big data applications provide convenience for people's life and work style, but in the process of data publishing, personal privacy information, such as consumption records, social relations, and so on, are collected by service providers all the time, and users' privacy is threatened greatly. Aiming at the significant relief of data processing pressure on single server, we propose a multi-cluster distributed differential privacy data publishing method based on neural network (MCDP), which effectively improves the prediction accuracy and efficiency, and different privacy parameters between clusters guarantee the flexibility of the protocol. Especially, because the central server stores statistical data after differential privacy processing, it does not collect individual privacy data, even if the central server is attacked, the user data will not be leaked. Experiments show that MCDP has obvious advantages in privacy processing efficiency, privacy protection intensity, prediction accuracy and prediction efficiency.

Key words: data publishing, differential privacy, service collaboration, neural network, multi-cluster, distribution

中图分类号:

TP18

陈思, 付安民, 柯海峰, 等. MCDP:基于神经网络的多集群分布式差分隐私数据发布方法[J]. 电子学报, 2020, 48(12): 2297-2303.

CHEN Si, FU An-min, KE Hai-feng, et al. MCDP:Multi-Cluster Differential Privacy Data Publishing Method Based on Neural Network[J]. Acta Electronica Sinica, 2020, 48(12): 2297-2303.

参考文献

[1] YU S,ZHOU W,GUO S,et al.A feasible IP traceback framework through dynamic deterministic packet marking[J].IEEE Transactions on Computers,2016,65(5):1418-1427.
[2] 杨高明,朱海明,方贤进,等.局部差分隐私约束的关联属性不变后随机响应扰动[J].电子学报,2019,47(5):105-111. Yang Gao-ming,Zhu Hai-ming,Fang Xie-jin,et al.Invariant post-random response perturbation for correlated attributes under local differential privacy constraint[J].Acta Electronica Sinica,2019,47(5):105-111.(in Chinese)
[3] 鲜征征,李启良,黄晓宇,等.融合显/隐式信任协同过滤算法的差分隐私保护[J].电子学报,2018,46(12):236-245. Xian Zheng-zheng,Li Qi-liang,Huang Xiao-yu,et al.Differential privacy protection for collaborative filtering algorithms with explicit and implicit trust[J].Acta Electronica Sinica,2018,46(12):236-245.(in Chinese)
[4] FU A M,YU S,ZHANG Y Q,et al.NPP:a new privacy-aware public auditing scheme for cloud data sharing with group users[J].IEEE Transactions on Big Data,DOI:10.1109/TBDATA.2017.2701347,2017.
[5] OGANIAN A,DOMINGO-FERRY J.Local synthesis for disclosure limitation that satisfies probabilistic k-anonymity criterion[J].Transactions on Data Privacy,2017,10(1):61-81.
[6] SORIA-COMAS J,DOMINGO-FERRER J,SANCHEZ D,et al.t-closeness through microaggregation:strict privacy with enhanced utility preservation[J].IEEE Transactions on Knowledge and Data Engineering,2015,27(11):3098-3110.
[7] DWORK C.Differential privacy[J].Lecture Notes in Computer Science,2006,26(2):1-12.
[8] YIN C,XI J,SUN R,et al.Location privacy protection based on differential privacy strategy for big data in industrial Internet of Things[J].IEEE Transactions on Industrial Informatics,2017,14(8):3628-3636.
[9] QU Y Y,YU S,GAO L X,et al.Big data set privacy preserving through sensitive attribute-based grouping[A].International Conference on Communications (ICC)[C].Paris,France:IEEE,2017.1-6.
[10] DRAKONAKIS K,ILIA P,IOANNIDIS S,et al.Please forget where I was last summer:the privacy risks of public location (meta) data[A].26th Annual Network and Distributed System Security Symposium (NDSS)[C].San Diego,USA:ISOC,2019.1-15.
[11] YE Q Q,HU H B,MENG X F,et al.PrivKV:key-value data collection with local differential privacy[A].Symposium on Security and Privacy (S&P)[C].San Francisco,USA:IEEE,2019.1-15.
[12] DUAN Y,YOUDAO N E,CANNY J,et al.P4P:practical large-scale privacy-preserving distributed computation robust against malicious users[A].19th USENIX Security Symposium (USENIX)[C].Washington,USA:ACM,2010.1-15.
[13] NI L,LI C,WANF X,et al.DP-MCDBSCAN:differential privacy preserving multi-core DBSCAN clustering for network user data[J].IEEE Access,2018,6:21053-21063.
[14] LV C,XING Y,ZHAN J,et al.Levenberg-marquardt backpropagation training of multilayer neural networks for state estimation of a safety critical cyber-physical system[J].IEEE Transactions on Industrial Informatics,2017,14(8):3436-3446.
[15] LICHMAN M.UCI Machine Learning Repository[EB/OL]:http://archive.ics.uci.edu/ml,2013.
[16] GREFF K,SRIVASTAVA R K,KOUTNIK J,et al.LSTM:a search space odyssey[J].IEEE Transactions on Neural Networks and Learning Systems,2016,28(10):2222-2232.

MCDP:基于神经网络的多集群分布式差分隐私数据发布方法

MCDP:Multi-Cluster Differential Privacy Data Publishing Method Based on Neural Network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	曾卓, 汪成亮, 马飞. 基于差分隐私的活动模式保护与时空轨迹发布方法[J]. 电子学报, 2023, 51(3): 552-563.
[2]	黄赟, 张帆, 郭威, 陈立, 羊光. 一种基于数据标准差的卷积神经网络量化方法[J]. 电子学报, 2023, 51(3): 639-647.
[3]	张金颢, 周恒, 张守龙, 蒋廷勇, 王胜涛, 刘真. 基于仿真及神经网络的大型电磁脉冲模拟器近区场计算[J]. 电子学报, 2023, 51(3): 712-719.
[4]	吕杭, 蒋明峰, 李杨, 张鞠成, 王志康. 基于混合时频域特征的卷积神经网络心律失常分类方法的研究[J]. 电子学报, 2023, 51(3): 701-711.
[5]	杨利平, 侯振威, 辜小花, 郝峻永. 弱标签声音事件检测的空间-通道特征表征与自注意池化[J]. 电子学报, 2023, 51(2): 297-306.
[6]	王子为, 鲁继文, 周杰. 基于自适应梯度优化的二值神经网络[J]. 电子学报, 2023, 51(2): 257-266.
[7]	许新征, 李杉. 基于特征膨胀卷积模块的轻量化技术研究[J]. 电子学报, 2023, 51(2): 355-364.
[8]	丁琪, 田萱, 孙国栋. 基于注意力增强的热点感知新闻推荐模型[J]. 电子学报, 2023, 51(1): 93-104.
[9]	张永梅, 孙捷. 基于动静态特征双输入神经网络的咳嗽声诊断COVID-19算法[J]. 电子学报, 2023, 51(1): 202-212.
[10]	袁海英, 成君鹏, 曾智勇, 武延瑞. Mobile_BLNet：基于Big-Little Net的轻量级卷积神经网络优化设计[J]. 电子学报, 2023, 51(1): 180-191.
[11]	王神龙, 雍宇, 吴晨睿. 基于伪孪生神经网络的低纹理工业零件6D位姿估计[J]. 电子学报, 2023, 51(1): 192-201.
[12]	王硕, 王坚, 王亚男, 宋亚飞. 一种基于特征融合的恶意代码快速检测方法[J]. 电子学报, 2023, 51(1): 57-66.
[13]	吴靖, 叶晓晶, 黄峰, 陈丽琼, 王志锋, 刘文犀. 基于深度学习的单帧图像超分辨率重建综述[J]. 电子学报, 2022, 50(9): 2265-2294.
[14]	毛国君, 王者浩, 黄山, 王翔. 基于剪边策略的图残差卷积深层网络模型[J]. 电子学报, 2022, 50(9): 2205-2214.
[15]	张少波, 原刘杰, 毛新军, 朱更明. 基于本地差分隐私的K-modes聚类数据隐私保护方法[J]. 电子学报, 2022, 50(9): 2181-2188.