A Framework for Evaluating Image Obfuscation under Deep Learning-Assisted Privacy Attacks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

A Framework for Evaluating Image Obfuscation under Deep Learning-Assisted Privacy Attacks

Résumé

Computer vision applications such as object detection and recognition, allow machines to visualize and perceivetheir environments. Nevertheless, these applications are guidedby learning-based methods that require capturing, storing and processing large amounts of images thus rendering privacy and anonymity a major concern. In return, image obfuscation techniques (i.e., pixelating, blurring, and masking) have been developed to protect the sensitive information in images. In thispaper, we propose a framework to evaluate and recommend the most robust obfuscation techniques in a specific domain of application. The proposed framework reconstructs obfuscated faces via deep learning-assisted attacks and assesses the reconstructions using structural/identity-based metrics. To evaluate and validate our approach, we conduct our experiments on a publicly available celebrity faces dataset. The obfuscation techniques considered are pixelating, blurring and masking. We evaluate the faces reconstructions against five deep learning-assisted privacy attackers. The most resilient obfuscation technique is recommended with regard to structural and identity-based metrics
Fichier non déposé

Dates et versions

hal-02952669 , version 1 (29-09-2020)

Identifiants

  • HAL Id : hal-02952669 , version 1

Citer

Jimmy Tekli, Bechara Al Bouna, Raphael Couturier, Gilbert Tekli, Zeinab Al Zein, et al.. A Framework for Evaluating Image Obfuscation under Deep Learning-Assisted Privacy Attacks. International Conference on Privacy, Security and Trust, Aug 2019, Fredericton, Canada. ⟨hal-02952669⟩
35 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More