Puzzling Face Verification Algorithms for Privacy Protection

Binod Bhattarai 1 Alexis Mignon 1 Frédéric Jurie 1 Teddy Furon 2
1 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
2 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : This paper presents a new approach for de-identifying face images, \ie for preventing automatic matching with public face collections. The overall motivation is to offer tools for privacy protection on social networks. We address this question by drawing a parallel between face de-identification and oracle attacks in digital watermarking. In our case, the identity of the face is seen as the watermark to be removed. Inspired by oracle attacks, we forge de-identified faces by superimposing a collection of carefully designed noise patterns onto the original face. The modification of the image is controlled to minimize the probability of good recognition while minimizing the distortion. In addition, these de-identified images are -- by construction -- made robust to counter attacks such as blurring. We present an experimental validation in which we de-identify LFW faces and show that resulting images are still recognized by human beings while deceiving a state-of-the-art face recognition algorithm.
Complete list of metadatas

https://hal.inria.fr/hal-01066070
Contributor : Teddy Furon <>
Submitted on : Friday, December 5, 2014 - 11:26:53 AM
Last modification on : Thursday, February 7, 2019 - 5:37:13 PM
Long-term archiving on : Monday, March 9, 2015 - 6:02:41 AM

File

privacy_wifs2014.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01066070, version 1

Citation

Binod Bhattarai, Alexis Mignon, Frédéric Jurie, Teddy Furon. Puzzling Face Verification Algorithms for Privacy Protection. IEEE Workshop on Information Forensics and Security, Dec 2014, Atlanta, United States. ⟨hal-01066070⟩

Share

Metrics

Record views

620

Files downloads

313