Interpretable Machine Learning for Privacy-Preserving Pervasive Systems

被引：8

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], [No title captured]
[2] [Anonymous], [No title captured]
[3] Doshi-Velez Finale., 2017, arXiv: Machine Learning
[4] Differential privacy: A survey of results
Dwork, Cynthia
[J]. THEORY AND APPLICATIONS OF MODELS OF COMPUTATION, PROCEEDINGS, 2008, 4978 : 1 - 19
[5] Guyon I., 2003, Journal of Machine Learning Research, V3, P1157, DOI 10.1162/153244303322753616
[6] Kelley P.G., 2008, Proceedings of the 1st ACM Workshop on Workshop on Aisec, P11
[7] Private traits and attributes are predictable from digital records of human behavior
Kosinski, Michal
Stillwell, David
Graepel, Thore
[J]. PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2013, 110 (15) : 5802 - 5805
[8] Kulesza T., 2015, P 20 INT C INT US IN, P126, DOI DOI 10.1145/2678025.2701399
[9] Kulesza T, 2013, S VIS LANG HUM CEN C, P3, DOI 10.1109/VLHCC.2013.6645235
[10] Lim BY, 2010, UBICOMP 2010: PROCEEDINGS OF THE 2010 ACM CONFERENCE ON UBIQUITOUS COMPUTING, P13

← 1 2 →