.png){kind=icon}
.png){kind=icon}
Return
Reconstruct face from features based on genetic algorithm using GAN generator as a distribution constraint
.png){kind=icon}
PRE
AI
DOI：10.1016/j.cose.2022.103026.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Face recognition based on deep convolutional neural networks (CNN) shows superior accuracy perfor-mance attributed to the high discriminative features extracted. Yet, the security and privacy of the ex-tracted features from deep learning models (deep features) have often been overlooked. This paper pro-poses the reconstruction of face images from deep features without accessing the CNN network config-urations as a constrained optimization problem. Such optimization minimizes the distance between the features extracted from the original face image and the reconstructed face image. Instead of directly solv-ing the optimization problem in the image space, we innovatively reformulate the problem by looking for a latent vector of a generative adversarial networks (GAN) generator, then use it to generate the face image. The GAN generator serves a dual role in this novel framework, i.e., face distribution constraint of the optimization goal and a face generator. To solve this optimization problem, We present an optimiza-tion approach based on a Genetic Algorithm. On top of the novel optimization task, we also propose an attack pipeline to impersonate the target user based on the generated face image. Our results show that the generated face images can achieve a state-of-the-art successful attack rate of 99.33% on Labeled Faces in the Wild (LFW) under type-I attack at a false accept rate of 0.1%. Our work sheds light on biometric deployment to meet privacy-preserving and security policies.(c) 2022 Elsevier Ltd. All rights reserved.
Keywords:
Face recognition
Template security
Deep networks
Deep templates
Distribution constraint
GAN
Journal
C
IF:
5.4
Papers:
4.6K
Citations:
1.4W
Organization
View more organizations