Learning to Conceal: A Deep Learning Based Method for Preserving Privacy and Avoiding Prejudice
This addresses privacy and bias prevention in image-based systems, though it appears incremental as it builds on existing VAE methods.
The paper tackles the problem of concealing personal attributes like gender, age, and ethnicity from images while preserving other details, using a variational autoencoder that avoids learning these attributes by directly adding labels to the latent vector, resulting in an encoding that lacks the concealed information.
In this paper, we introduce a learning model able to conceals personal information (e.g. gender, age, ethnicity, etc.) from an image, while maintaining any additional information present in the image (e.g. smile, hair-style, brightness). Our trained model is not provided the information that it is concealing, and does not try learning it either. Namely, we created a variational autoencoder (VAE) model that is trained on a dataset including labels of the information one would like to conceal (e.g. gender, ethnicity, age). These labels are directly added to the VAE's sampled latent vector. Due to the limited number of neurons in the latent vector and its appended noise, the VAE avoids learning any relation between the given images and the given labels, as those are given directly. Therefore, the encoded image lacks any of the information one wishes to conceal. The encoding may be decoded back into an image according to any provided properties (e.g. a 40 year old woman). The proposed architecture can be used as a mean for privacy preserving and can serve as an input to systems, which will become unbiased and not suffer from prejudice. We believe that privacy and discrimination are two of the most important aspects in which the community should try and develop methods to prevent misuse of technological advances.