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: https://github.com/chi0tzp/FALCO.

Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization / Barattin, Simone; Tzelepis, Christos; Patras, Ioannis; Sebe, Nicu. - (2023), pp. 8001-8010. (Intervento presentato al convegno CVPR tenutosi a Vancouver, Canada nel 17-24 June 2023) [10.1109/CVPR52729.2023.00773].

Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization

Sebe, Nicu
2023-01-01

Abstract

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: https://github.com/chi0tzp/FALCO.
2023
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Piscataway, NJ USA
IEEE
979-8-3503-0129-8
979-8-3503-0130-4
Barattin, Simone; Tzelepis, Christos; Patras, Ioannis; Sebe, Nicu
Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization / Barattin, Simone; Tzelepis, Christos; Patras, Ioannis; Sebe, Nicu. - (2023), pp. 8001-8010. (Intervento presentato al convegno CVPR tenutosi a Vancouver, Canada nel 17-24 June 2023) [10.1109/CVPR52729.2023.00773].
File in questo prodotto:
File Dimensione Formato  
Barattin_Attribute-Preserving_Face_Dataset_Anonymization_via_Latent_Code_Optimization_CVPR_2023_paper (1).pdf

accesso aperto

Descrizione: This CVPR paper is the Open Access version, provided by the Computer Vision Foundation
Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 7.12 MB
Formato Adobe PDF
7.12 MB Adobe PDF Visualizza/Apri
Attribute-Preserving_Face_Dataset_Anonymization_via_Latent_Code_Optimization.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.16 MB
Formato Adobe PDF
1.16 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/395089
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 1
social impact