TY - JOUR
T1 - An AI-Enabled Three-Party Game Framework for Guaranteed Data Privacy in Mobile Edge Crowdsensing of IoT
AU - Xiong, Jinbo
AU - Zhao, Mingfeng
AU - Bhuiyan, Md Zakirul Alam
AU - Chen, Lei
AU - Tian, Youliang
N1 - Publisher Copyright:
© 2005-2012 IEEE.
PY - 2021/2
Y1 - 2021/2
N2 - The mobile crowdsensing (MCS) technology with a large number of Internet of Things (IoT) devices provides an economic and efficient solution to participation in coordinated large-scale sensing tasks. Edge computing powers MCS to form the mobile edge crowdsensing (MECS) framework. Privacy disclosure of sensing data in multiple stages is a significant challenge in the MECS. To tackle this issue, combining machine learning with game theory, in this article, we propose an artificial intelligence (AI)-enabled three-party game (ATG) framework for guaranteed data privacy in the MECS of IoT. Specifically, based on the random forest classifier and the k-anonymity algorithm, we propose a classification-anonymity model that effectively guarantees the privacy of sensitive data. Moreover, we construct a three-party game model for analyzing the data privacy leakage in different phases in the MECS. Finally, we conduct numerical and theoretical analyses and ample simulations. The results indicate that the ATG framework is effective and efficient, and better suited to the MECS of IoT.
AB - The mobile crowdsensing (MCS) technology with a large number of Internet of Things (IoT) devices provides an economic and efficient solution to participation in coordinated large-scale sensing tasks. Edge computing powers MCS to form the mobile edge crowdsensing (MECS) framework. Privacy disclosure of sensing data in multiple stages is a significant challenge in the MECS. To tackle this issue, combining machine learning with game theory, in this article, we propose an artificial intelligence (AI)-enabled three-party game (ATG) framework for guaranteed data privacy in the MECS of IoT. Specifically, based on the random forest classifier and the k-anonymity algorithm, we propose a classification-anonymity model that effectively guarantees the privacy of sensitive data. Moreover, we construct a three-party game model for analyzing the data privacy leakage in different phases in the MECS. Finally, we conduct numerical and theoretical analyses and ample simulations. The results indicate that the ATG framework is effective and efficient, and better suited to the MECS of IoT.
KW - Machine learning
KW - mobile edge crowdsensing (MECS)
KW - Nash equilibrium (NE)
KW - privacy protection
KW - three-party game (TG) model
UR - http://www.scopus.com/inward/record.url?scp=85096782527&partnerID=8YFLogxK
U2 - 10.1109/TII.2019.2957130
DO - 10.1109/TII.2019.2957130
M3 - Article
AN - SCOPUS:85096782527
SN - 1551-3203
VL - 17
SP - 922
EP - 933
JO - IEEE Transactions on Industrial Informatics
JF - IEEE Transactions on Industrial Informatics
IS - 2
M1 - 8918437
ER -