An Efficient Differential Privacy Logistic Classification Mechanism

被引：19

作者：

Huang, Wen ^{[1
]}

Zhou, Shijie ^{[1
]}

Liao, Yongjian ^{[1
]}

Chen, Hongjie ^{[1
]}

机构：

[1] Univ Elect Sci & Technol China, Sch Informat & Software Engn, Chengdu 610054, Sichuan, Peoples R China

来源：

IEEE INTERNET OF THINGS JOURNAL | 2019年 / 6卷 / 06期

关键词：

Differential privacy; logistic classification;

D O I：

10.1109/JIOT.2019.2940103

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The logistic model is a very elementary and important model in the field of machine learning. In this article, an efficient differential privacy logistic classification mechanism is proposed. The proposed mechanism is better than object function perturbation mechanism in terms of running time and accuracy. Regarding accuracy, the proposed mechanism's accuracy is almost the same as the no differential privacy (non-dp) mechanism, and the proposed mechanism is better than that of the object function perturbation mechanism in both the test accuracy and the train accuracy. As for the running time of the training model, the proposed mechanism is better than the object function mechanism and is the same as the non-dp mechanism.

引用

页码：10620 / 10626

页数：7

共 19 条

[1] [Anonymous], 2016, ARXIV160207387
[2] Chaudhuri K, 2011, J MACH LEARN RES, V12, P1069
[3] Chaudhuri Kamalika, 2008, Advances in Neural Information Processing Systems, V21
[4] Chen R, 2016, PROC INT CONF DATA, P289, DOI 10.1109/ICDE.2016.7498248
[5] Friedman A., 2010, KDD 10, Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, 2528 July 2010, P493, DOI [10.1145/1835804.1835868, DOI 10.1145/1835804.1835868]
[6] Hardt M, 2013, STOC'13: PROCEEDINGS OF THE 2013 ACM SYMPOSIUM ON THEORY OF COMPUTING, P331
[7] Jain Prateek, 2012, C LEARN THEOR
[8] Differential privacy based on importance weighting
Ji, Zhanglong
Elkan, Charles
[J]. MACHINE LEARNING, 2013, 93 (01) : 163 - 183
[9] Jiang XQ, 2013, TRANS DATA PRIV, V6, P19
[10] Kairouz P, 2014, ADV NEUR IN, V27

← 1 2 →