Lightweight privacy-preserving ensemble classification for face recognition

The development of machine learning technology and visual sensors is promoting the wider applications of face recognition into our daily life. However, if the face features in the servers are abused by the adversary, our privacy and wealth can be faced with great threat. Many security experts have p...

Full description

Saved in:
Bibliographic Details
Main Authors: MA, Zhuo, LIU, Yang, LIU, Ximeng, MA, Jianfeng, REN, Kui
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2019
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/4405
https://ink.library.smu.edu.sg/context/sis_research/article/5408/viewcontent/101109JIOT20192905555.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-5408
record_format dspace
spelling sg-smu-ink.sis_research-54082020-04-15T04:59:15Z Lightweight privacy-preserving ensemble classification for face recognition MA, Zhuo LIU, Yang LIU, Ximeng MA, Jianfeng REN, Kui The development of machine learning technology and visual sensors is promoting the wider applications of face recognition into our daily life. However, if the face features in the servers are abused by the adversary, our privacy and wealth can be faced with great threat. Many security experts have pointed out that, by 3-D-printing technology, the adversary can utilize the leaked face feature data to masquerade others and break the E-bank accounts. Therefore, in this paper, we propose a lightweight privacy-preserving adaptive boosting (AdaBoost) classification framework for face recognition (POR) based on the additive secret sharing and edge computing. First, we improve the current additive secret sharing-based exponentiation and logarithm functions by expanding the effective input range. Then, by utilizing the protocols, two edge servers are deployed to cooperatively complete the ensemble classification of AdaBoost for face recognition. The application of edge computing ensures the efficiency and robustness of POR. Furthermore, we prove the correctness and security of our protocols by theoretic analysis. And experiment results show that, POR can reduce about 58% computation error compared with the existing differential privacy-based framework. 2019-06-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/4405 info:doi/10.1109/JIOT.2019.2905555 https://ink.library.smu.edu.sg/context/sis_research/article/5408/viewcontent/101109JIOT20192905555.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Adaptive boosting (AdaBoost) Additive secret sharing Face recognition Privacy-preserving Information Security Numerical Analysis and Scientific Computing
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Adaptive boosting (AdaBoost)
Additive secret sharing
Face recognition
Privacy-preserving
Information Security
Numerical Analysis and Scientific Computing
spellingShingle Adaptive boosting (AdaBoost)
Additive secret sharing
Face recognition
Privacy-preserving
Information Security
Numerical Analysis and Scientific Computing
MA, Zhuo
LIU, Yang
LIU, Ximeng
MA, Jianfeng
REN, Kui
Lightweight privacy-preserving ensemble classification for face recognition
description The development of machine learning technology and visual sensors is promoting the wider applications of face recognition into our daily life. However, if the face features in the servers are abused by the adversary, our privacy and wealth can be faced with great threat. Many security experts have pointed out that, by 3-D-printing technology, the adversary can utilize the leaked face feature data to masquerade others and break the E-bank accounts. Therefore, in this paper, we propose a lightweight privacy-preserving adaptive boosting (AdaBoost) classification framework for face recognition (POR) based on the additive secret sharing and edge computing. First, we improve the current additive secret sharing-based exponentiation and logarithm functions by expanding the effective input range. Then, by utilizing the protocols, two edge servers are deployed to cooperatively complete the ensemble classification of AdaBoost for face recognition. The application of edge computing ensures the efficiency and robustness of POR. Furthermore, we prove the correctness and security of our protocols by theoretic analysis. And experiment results show that, POR can reduce about 58% computation error compared with the existing differential privacy-based framework.
format text
author MA, Zhuo
LIU, Yang
LIU, Ximeng
MA, Jianfeng
REN, Kui
author_facet MA, Zhuo
LIU, Yang
LIU, Ximeng
MA, Jianfeng
REN, Kui
author_sort MA, Zhuo
title Lightweight privacy-preserving ensemble classification for face recognition
title_short Lightweight privacy-preserving ensemble classification for face recognition
title_full Lightweight privacy-preserving ensemble classification for face recognition
title_fullStr Lightweight privacy-preserving ensemble classification for face recognition
title_full_unstemmed Lightweight privacy-preserving ensemble classification for face recognition
title_sort lightweight privacy-preserving ensemble classification for face recognition
publisher Institutional Knowledge at Singapore Management University
publishDate 2019
url https://ink.library.smu.edu.sg/sis_research/4405
https://ink.library.smu.edu.sg/context/sis_research/article/5408/viewcontent/101109JIOT20192905555.pdf
_version_ 1770574699012554752