City Research Online

Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization

Barattin, S., Tzelepis, C. ORCID: 0000-0002-2036-9089, Patras, I. & Sebe, N. (2023). Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization. In: Computer Vision and Pattern Recognition. IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023, 18-22 Jun 2023, Vancouver, Canada. doi: 10.1109/cvpr52729.2023.00773


This work addresses the problem of anonymizing the identity of faces in a dataset of images, such that the privacy of those depicted is not violated, while at the same time the dataset is useful for downstream task such as for training machine learning models. To the best of our knowledge, we are the first to explicitly address this issue and deal with two major drawbacks of the existing state-of-the-art approaches, namely that they (i) require the costly training of additional, purpose-trained neural networks, and/or (ii) fail to retain the facial attributes of the original images in the anonymized counterparts, the preservation of which is of paramount importance for their use in downstream tasks. We accordingly present a task-agnostic anonymization procedure that directly optimizes the images' latent representation in the latent space of a pretrained GAN. By optimizing the latent codes directly, we ensure both that the identity is of a desired distance away from the original (with an identity obfuscation loss), whilst preserving the facial attributes (using a novel feature-matching loss in FaRL's [48] deep feature space). We demonstrate through a series of both qualitative and quantitative experiments that our method is capable of anonymizing the identity of the images whilst-crucially-better-preserving the facial attributes. We make the code and the pretrained models publicly available at:

Publication Type: Conference or Workshop Item (Paper)
Additional Information: © 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Subjects: H Social Sciences > HN Social history and conditions. Social problems. Social reform
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology
Departments: School of Science & Technology > Computer Science
[thumbnail of cvpr23_falco_preprint.pdf]
Text - Accepted Version
Download (14MB) | Preview


Add to AnyAdd to TwitterAdd to FacebookAdd to LinkedinAdd to PinterestAdd to Email


Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login