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

By Vahid Mirjalili, Sebastian Raschka, Anoop M. Namboodiri, Arun A. Ross. 2017

117 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

A Hybrid Model for Identity Obfuscation by Face Replacement (2018, background): “he L1 term5. Then, for the discriminator, we have the following losses: LD = LD adv = L bce(D(I O);1) + L (D(G(I;F));0); (8) Note that de-identication losses derived from identity verication models [38] are not applicable to our approach. Since such verication models are usually trained by real imag”
On the Global Optima of Kernelized Adversarial Representation Learning (2019, background): “of approaches [6, 28, 3, 26, 20, 23, 1] have used and argued [18] for explicit adversarial networks as a proxy to mimic an unknown adversary seeking to extract the sensitive attributes from the encoded data.”
FlowSAN: Privacy-Enhancing Semi-Adversarial Networks to Confound Arbitrary Face-Based Gender Classifiers (2019, methodology): “In our previous work [44], we empirically showed that the ability to predict gender information, using an unseen gender classifier from outputs of the SAN model, is successfully diminished.”
Deep Face Recognition: A Survey (2018, background): “Recently, the pioneer works such as Semi-Adversarial Networks [298], [299], [285] have explored to generate a recognizable biometric templates that can hidden some of the private information presented in the facial images.”
Generative Adversarial Networks–Enabled Human–Artificial Intelligence Collaborative Applications for Creative and Design Industries: A Systematic Review of Current Approaches and Trends (2021, background): “The emergence of the family of generative models has created another potential avenue for the erosion of trust, with much-publicized examples such as systems to hide from facial detection systems (Mirjalili et al., 2017; Johnson, 2020) or the generation of highly realistic fake images (Zhu et al.”
Racial Faces in the Wild: Reducing Racial Bias by Information Maximization Adaptation Network (2018, background): “unequal-training [9] and suppressing attributes [8, 43, 44, 42], have made effort to mitigate racial and gender bias in several computer vision tasks, this study remains to be vacant in FR.”