Differential Privacy in Privacy-Preserving Big Data and Learning: Challenge and Opportunity

被引:4
作者
Jiang, Honglu [1 ]
Gao, Yifeng [1 ]
Sarwar, S. M. [1 ]
GarzaPerez, Luis [1 ]
Robin, Mahmudul [1 ]
机构
[1] Univ Texas Rio Grande Valley, Edinburg, TX 78504 USA
来源
SILICON VALLEY CYBERSECURITY CONFERENCE, SVCC 2021 | 2022年 / 1536卷
关键词
Differential privacy; Deep learning; Big data;
D O I
10.1007/978-3-030-96057-5_3
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Differential privacy (DP) has become the de facto standard of privacy preservation due to its strong protection and sound mathematical foundation, which is widely adopted in different applications such as big data analysis, graph data process, machine learning, deep learning, and federated learning. Although DP has become an active and influential area, it is not the best remedy for all privacy problems in different scenarios. Moreover, there are also some misunderstanding, misuse, and great challenges of DP in specific applications. In this paper, we point out a series of limits and open challenges of corresponding research areas. Besides, we offer potentially new insights and avenues on combining differential privacy with other effective dimension reduction techniques and secure multiparty computing to clearly define various privacy models.
引用
收藏
页码:33 / 44
页数:12
相关论文
共 25 条
[1]   Deep Learning with Differential Privacy [J].
Abadi, Martin ;
Chu, Andy ;
Goodfellow, Ian ;
McMahan, H. Brendan ;
Mironov, Ilya ;
Talwar, Kunal ;
Zhang, Li .
CCS'16: PROCEEDINGS OF THE 2016 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, 2016, :308-318
[2]  
[Anonymous], 1977, Statistisk Tidskrift
[3]  
[Anonymous], 2007, ACM T KNOWL DISCOV D, DOI [10.1145/1217299.1217302, DOI 10.1145/1217299.1217302]
[4]   Local Differential Privacy for Deep Learning [J].
Arachchige, Pathum Chamikara Mahawaga ;
Bertok, Peter ;
Khalil, Ibrahim ;
Liu, Dongxi ;
Camtepe, Seyit ;
Atiquzzaman, Mohammed .
IEEE INTERNET OF THINGS JOURNAL, 2020, 7 (07) :5827-5842
[5]   On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation [J].
Bach, Sebastian ;
Binder, Alexander ;
Montavon, Gregoire ;
Klauschen, Frederick ;
Mueller, Klaus-Robert ;
Samek, Wojciech .
PLOS ONE, 2015, 10 (07)
[6]  
DAcquisto G., 2015, ENISA
[7]   Local Privacy and Statistical Minimax Rates [J].
Duchi, John C. ;
Jordan, Michael I. ;
Wainwright, Martin J. .
2013 IEEE 54TH ANNUAL SYMPOSIUM ON FOUNDATIONS OF COMPUTER SCIENCE (FOCS), 2013, :429-438
[8]  
Dwork C, 2006, LECT NOTES COMPUT SC, V4052, P1
[9]   Calibrating noise to sensitivity in private data analysis [J].
Dwork, Cynthia ;
McSherry, Frank ;
Nissim, Kobbi ;
Smith, Adam .
THEORY OF CRYPTOGRAPHY, PROCEEDINGS, 2006, 3876 :265-284
[10]  
Geyer RC., 2017, ABS171207557 CORR