Achieving Anonymity Against Major Face Recognition Algorithms

Benedikt Driessen; Markus Dürmuth

Paper 2013/009

Achieving Anonymity Against Major Face Recognition Algorithms

Benedikt Driessen and Markus Dürmuth

Abstract

An ever-increasing number of personal photos is stored online. This trend can be problematic, because face recognition software can undermine user privacy in unexpected ways. Face de-identification aims to prevent automatic recognition of faces thus improving user privacy, but previous work alters the image in a way that makes them indistinguishable for both computers and humans, which prevents a wide-spread use. We propose a method for de-identification of images that effectively prevents face recognition software (using the most popular and effective algorithms) from identifying people, but still allows human recognition. We evaluate our method experimentally by adapting the CSU framework and using the FERET database. We show that we are able to achieve strong de-identification while maintaining reasonable image quality.

Metadata

Available format(s): PDF
Publication info: Published elsewhere. Unknown where it was published
Keywords: Face recognition Anonymity
Contact author(s): benedikt driessen @ rub de
History: 2013-01-12: received
Short URL: https://ia.cr/2013/009
License: CC BY

BibTeX

@misc{cryptoeprint:2013/009,
      author = {Benedikt Driessen and Markus Dürmuth},
      title = {Achieving Anonymity Against Major Face Recognition Algorithms},
      howpublished = {Cryptology {ePrint} Archive, Paper 2013/009},
      year = {2013},
      url = {https://eprint.iacr.org/2013/009}
}