ML Anthology

Vulnerabilities in Binary Face Template

Yi Cheng Feng, Pong Chi Yuen
CVPRW 2012 pp. 105-110
doi:10.1109/CVPRW.2012.6239223 /cvprw/2012/feng2012cvprw-vulnerabilities/

Abstract

It is generally believed that original face image is hard to be reconstructed from its binary face template and therefore, binary face template is secure. In this paper, we find that binary template is not secure and can be attacked by a masquerade attack. A masquerade face image, which may not "look" similar with the original image, is constructed from binary templates and then employed to access the system. Experimental results show that the successful attacking rate on CMU-PIE and FRGC databases are 100% and 77.14% in around 8 and 33 seconds in a personal computer, respectively.

CVPRW Semantic Scholar

Cite

Text

Feng and Yuen. "Vulnerabilities in Binary Face Template." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2012. doi:10.1109/CVPRW.2012.6239223

Markdown

[Feng and Yuen. "Vulnerabilities in Binary Face Template." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2012.](https://mlanthology.org/cvprw/2012/feng2012cvprw-vulnerabilities/) doi:10.1109/CVPRW.2012.6239223

BibTeX

@inproceedings{feng2012cvprw-vulnerabilities,
  title     = {{Vulnerabilities in Binary Face Template}},
  author    = {Feng, Yi Cheng and Yuen, Pong Chi},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2012},
  pages     = {105-110},
  doi       = {10.1109/CVPRW.2012.6239223},
  url       = {https://mlanthology.org/cvprw/2012/feng2012cvprw-vulnerabilities/}
}