Interpretable Machine Learning for Privacy-Preserving Pervasive Systems

被引：9

作者：

Baron, Benjamin ^{[1
]}

Musolesi, Mirco ^{[2
]}

机构：

[1] UCL, London, England

[2] UCL, Data Sci, London, England

来源：

IEEE PERVASIVE COMPUTING | 2020年 / 19卷 / 01期

基金：

英国工程与自然科学研究理事会;

关键词：

Privacy; Machine learning; Task analysis; Data privacy; Computational modeling; Feature extraction;

D O I：

10.1109/MPRV.2019.2918540

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Our everyday interactions with pervasive systems generate traces that capture various aspects of human behavior and enable machine learning algorithms to extract latent information about users. In this paper, we propose a machine learning interpretability framework that enables users to understand how these generated traces violate their privacy.

引用

页码：73 / 82

页数：10

共 20 条

[1]

[Anonymous], 2016, SOK SCI SECURITY PRI

[2]

[Anonymous], DATASET SHIFT MACHIN

[3]

[Anonymous], [No title captured]

[4]

[Anonymous], [No title captured]

[5]

Doshi-Velez Finale., 2017, arXiv: Machine Learning

[6] Differential privacy: A survey of results [J].

Dwork, Cynthia .

THEORY AND APPLICATIONS OF MODELS OF COMPUTATION, PROCEEDINGS, 2008, 4978 :1-19

[7]

Guyon I., 2003, Journal of Machine Learning Research, V3, P1157, DOI 10.1162/153244303322753616

[8]

Kelley P. G., 2008, P 1 ACM WORKSH AISEC, P11, DOI DOI 10.1145/1456377.1456380

[9] Private traits and attributes are predictable from digital records of human behavior [J].

Kosinski, Michal ;

Stillwell, David ;

Graepel, Thore .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2013, 110 (15) :5802-5805

[10]

Kulesza T., 2015, P 20 INT C INTELLIGE, P126, DOI DOI 10.1145/2678025.2701399

← 1 2 →