On the Protection of Private Information in Machine Learning Systems: Two Recent Approches (Invited Paper)

被引：37

作者：

Abadi, Martin ^{[1
]}

Erlingsson, Ulfar ^{[1
]}

Goodfellow, Ian ^{[1
]}

McMahan, H. Brendan ^{[1
]}

Mironov, Ilya ^{[1
]}

Papernot, Nicolas ^{[1
,2
]}

Talwar, Kunal ^{[1
]}

Zhang, Li ^{[1
]}

机构：

[1] Google, Mountain View, CA 94043 USA

[2] Penn State Univ, University Pk, PA 16802 USA

来源：

2017 IEEE 30TH COMPUTER SECURITY FOUNDATIONS SYMPOSIUM (CSF) | 2017年

关键词：

D O I：

10.1109/CSF.2017.10

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

The recent, remarkable growth of machine learning has led to intense interest in the privacy of the data on which machine learning relies, and to new techniques for preserving privacy. However, older ideas about privacy may well remain valid and useful. This note reviews two recent works on privacy in the light of the wisdom of some of the early literature, in particular the principles distilled by Saltzer and Schroeder in the 1970s.

引用

页码：1 / 6

页数：6

共 38 条

[21]

Mironov I., 2017, CORR

[22]

Mironov Ilya, 2012, P 2012 ACM C COMP CO, P650, DOI DOI 10.1145/2382196.2382264

[23]

Neelakantan Arvind., 2015, CoRR

[24] Smooth Sensitivity and Sampling in Private Data Analysis [J].

Nissim, Kobbi ;

Raskhodnikova, Sofya ;

Smith, Adam .

STOC 07: PROCEEDINGS OF THE 39TH ANNUAL ACM SYMPOSIUM ON THEORY OF COMPUTING, 2007, :75-84

[25]

Papernot N, INT C LEARN REPR

[26]

Pathak M, 2010, P 23 INT C NEURAL IN, P1876

[27] Calibrating Data to Sensitivity in Private Data Analysis [J].

Proserpio, Davide ;

Goldberg, Sharon ;

McSherry, Frank .

PROCEEDINGS OF THE VLDB ENDOWMENT, 2014, 7 (08) :637-648

[28] Deep learning [J].

Rusk, Nicole .

NATURE METHODS, 2016, 13 (01) :35-35

[29]

Salimans T, 2016, ADV NEUR IN, V29

[30] PROTECTION OF INFORMATION IN COMPUTER SYSTEMS [J].

SALTZER, JH ;

SCHROEDER, MD .

PROCEEDINGS OF THE IEEE, 1975, 63 (09) :1278-1308

← 1 2 3 4 →