Semi-Adversarial Networks: Convolutional Autoencoders for Imparting Privacy to Face Images
This addresses privacy concerns for individuals in facial recognition systems by enabling selective obfuscation of sensitive attributes like gender, representing an incremental improvement in privacy-preserving techniques.
The paper tackles the problem of imparting privacy to face images by designing a convolutional autoencoder that perturbs images to maintain face recognition performance while confounding gender classification, achieving efficacy in extending gender privacy.
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 a pseudo gender classifier and a pseudo 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.