Semi-adversarial Networks: Convolutional Autoencoders for Imparting Privacy to Face Images

In this paper, we design and evaluate a convolutional autoencoder that perturbs an input face image to impart privacy to a subject. Specifically, the proposed autoencoder transforms an input face image such that the transformed image can be successfully used for face recognition but not for gender c...

Full description

Saved in:
Bibliographic Details
Published in:2018 International Conference on Biometrics (ICB) pp. 82 - 89
Main Authors: Mirjalili, Vahid, Raschka, Sebastian, Namboodiri, Anoop, Ross, Arun
Format: Conference Proceeding
Language:English
Published: IEEE 01.02.2018
Subjects:
autoencoder
biometrics
Decoding
Face
Face recognition
Perturbation methods
privacy
Prototypes
recognition
semi adversarial training
soft biometrics
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we design and evaluate a convolutional autoencoder that perturbs an input face image to impart privacy to a subject. Specifically, the proposed autoencoder transforms an input face image such that the transformed image can be successfully used for face recognition but not for gender classification. In order to train this autoencoder, we propose a novel training scheme, referred to as semi-adversarial training in this work. The training is facilitated by attaching a semi-adversarial module consisting of an auxiliary gender classifier and an auxiliary face matcher to the autoencoder. The objective function utilized for training this network has three terms: one to ensure that the perturbed image is a realistic face image; another to ensure that the gender attributes of the face are confounded; and a third to ensure that biometric recognition performance due to the perturbed image is not impacted. Extensive experiments confirm the efficacy of the proposed architecture in extending gender privacy to face images.
DOI:10.1109/ICB2018.2018.00023