Privacy Preserving Face Identification in the Cloud through Sparse Representation

Xin Jin 1 , ∗ , Yan Liu 1 , 2 , Xiaodong Li 1 , , Geng Zhao 1 , Yingya Chen 1 , and Kui Guo 1

1 Beijing Electronic Science and Technology Institute, Beijing 100070, China,

GOCPCCC Key Laboratory of Information Security, Beijing 100070, China

2 Xidian University, Xi’an, 710071, China

{jinxin,lxd}@besti.edu.cn

Abstract

  Nowadays, with tremendous visual media stored and even processed in the cloud, the privacy of visual media is also exposed to the cloud. In this paper we propose a private face identification method based on sparse representation. The identification is done in a secure way which protects both the privacy of the subjects and the confidentiality of the database. The face identification server in the cloud contains a list of registered faces. The surveillance client captures a face image and require the server to identify if the client face matches one of the suspects, but otherwise reveals no information to neither of the two parties. This is the first work that introduces sparse representation to the secure protocol of private face identification, which reduces the dimension of the face representation vector and avoid the patch based attack of a previous work. Besides, we introduce a secure Euclidean distance algorithm for the secure protocol. The experimental results reveal that the cloud server can return the identification results to the surveillance client without knowing anything about the client face image.

Gallery

client-1

The overview of our method. A third party face database is used to learn a dictionary. The face captured by the client and the faces in the list of the cloud server are represented sparse parameter vector. The Euclidean distance of the client face vector and each of the face vector in the server is computed in a privacy preserving way. The matching result is only known by the client. The cloud server learns nothing. 

Paper and Slides

pdf
, , , , , :Privacy Preserving Face Identification in the Cloud through Sparse Representation. CCBR : 160-167.

video

slides

BibTeX

@inproceedings{DBLP:conf/ccbr/JinLLZCG15,
  author    = {Xin Jin and
               Yan Liu and
               Xiaodong Li and
               Geng Zhao and
               Yingya Chen and
               Kui Guo},
  title     = {Privacy Preserving Face Identification in the Cloud through Sparse
               Representation},
  booktitle = {Biometric Recognition - 10th Chinese Conference, {CCBR} 2015, Tianjin,
               China, November 13-15, 2015, Proceedings},
  pages     = {160--167},
  year      = {2015},
  crossref  = {DBLP:conf/ccbr/2015},
  url       = {https://doi.org/10.1007/978-3-319-25417-3_20},
  doi       = {10.1007/978-3-319-25417-3_20},
  timestamp = {Sun, 21 May 2017 00:22:13 +0200},
  biburl    = {http://dblp.uni-trier.de/rec/bib/conf/ccbr/JinLLZCG15},
  bibsource = {dblp computer science bibliography, http://dblp.org}
}

 

发表评论

电子邮件地址不会被公开。 必填项已用*标注