Exploring Quality Camouflage for Social Images - Inria - Institut national de recherche en sciences et technologies du numérique
Communication Dans Un Congrès Année : 2020

Exploring Quality Camouflage for Social Images

Résumé

Social images can be misused in ways not anticipated or intended by the people who share them online. In particular, high-quality images can be driven to unwanted prominence by search engines or used to train unscrupulous AI. The risk of misuse can be reduced if photos can evade quality filtering, which is commonly carried out by automatic Blind Image Quality Assessment (BIQA) algorithms. The Pixel Privacy Task benchmarks privacy-protective approaches that shield images against unethical computer vision algorithms. In the 2020 task, participants are asked to develop quality camouflage methods that can effectively decrease the BIQA score of high-quality images while maintaining image appeal. The camouflage should not damage the image from the point of view of the user: it needs to be either imperceptible, or else to enhance the image visibly, to the human eye.
Fichier principal
Vignette du fichier
MediaEval20_paper_77-2.pdf (707.48 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03129778 , version 1 (03-02-2021)

Identifiants

  • HAL Id : hal-03129778 , version 1

Citer

Zhuoran Liu, Zhengyu Zhao, Martha Larson, Laurent Amsaleg. Exploring Quality Camouflage for Social Images. MediaEval 2020 - MediaEval Benchmarking Initiative for Multimedia Evaluation, Dec 2020, Online, United States. pp.1-3. ⟨hal-03129778⟩
96 Consultations
146 Téléchargements

Partager

More