Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

A Mean-Field Stackelberg Game Approach for Obfuscation Adoption in Empirical Risk Minimization

Abstract: 

Data ecosystems are becoming larger and more complex, while privacy concerns are threatening to erode their potential benefits. Recently, users have developed obfuscation techniques that issue fake search engine queries, undermine location tracking algorithms, or evade government surveillance. These techniques raise one conflict between each user and the machine learning algorithms which track the users, and one conflict between the users themselves. We use game theory to capture the first conflict with a Stackelberg game and the second conflict with a mean field game. Both are combined into a bi-level framework which quantifies accuracy using empirical risk minimization and privacy using differential privacy. We identify necessary and sufficient conditions under which 1) each user is incentivized to obfuscate if other users are obfuscating, 2) the tracking algorithm can avoid this by promising a level of privacy protection, and 3) this promise is incentive-compatible for the tracking algorithm.

up
0 users have voted:

Paper Details

Authors:
Jeffrey Pawlick, Quanyan Zhu
Submitted On:
9 November 2017 - 2:35pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Jeffrey Pawlick
Paper Code:
1561
Document Year:
2017
Cite

Document Files

GlobalSipPawlickZhu.pdf

(136 downloads)

Subscribe

[1] Jeffrey Pawlick, Quanyan Zhu, "A Mean-Field Stackelberg Game Approach for Obfuscation Adoption in Empirical Risk Minimization", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2275. Accessed: Jun. 19, 2018.
@article{2275-17,
url = {http://sigport.org/2275},
author = {Jeffrey Pawlick; Quanyan Zhu },
publisher = {IEEE SigPort},
title = {A Mean-Field Stackelberg Game Approach for Obfuscation Adoption in Empirical Risk Minimization},
year = {2017} }
TY - EJOUR
T1 - A Mean-Field Stackelberg Game Approach for Obfuscation Adoption in Empirical Risk Minimization
AU - Jeffrey Pawlick; Quanyan Zhu
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2275
ER -
Jeffrey Pawlick, Quanyan Zhu. (2017). A Mean-Field Stackelberg Game Approach for Obfuscation Adoption in Empirical Risk Minimization. IEEE SigPort. http://sigport.org/2275
Jeffrey Pawlick, Quanyan Zhu, 2017. A Mean-Field Stackelberg Game Approach for Obfuscation Adoption in Empirical Risk Minimization. Available at: http://sigport.org/2275.
Jeffrey Pawlick, Quanyan Zhu. (2017). "A Mean-Field Stackelberg Game Approach for Obfuscation Adoption in Empirical Risk Minimization." Web.
1. Jeffrey Pawlick, Quanyan Zhu. A Mean-Field Stackelberg Game Approach for Obfuscation Adoption in Empirical Risk Minimization [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2275