Transferability analysis of adversarial attacks on gender classification to face recognition: Fixed and variable attack perturbation

Autor: Zohra Rezgui, Amina Bassit, Raymond Veldhuis

Publikováno v: IET Biometrics, Vol 11, Iss 5, Pp 407-419 (2022)

Abstract Most deep learning‐based image classification models are vulnerable to adversarial attacks that introduce imperceptible changes to the input images for the purpose of model misclassification. It has been demonstrated that these attacks, ta

Externí odkaz: https://doaj.org/article/6cb3ccf0081846d488b882018f1b3d39

Describing Gender Equality in French Audiovisual Streams with a Deep Learning Approach

Autor: Jean Carrive, Zohra Rezgui, Géraldine Poels, David Doukhan

Publikováno v: VIEW Journal, 7(14), 103-122
VIEW Journal of European Television History and Culture, Vol 7, Iss 14, p 103 (2018)
VIEW Journal of European Television History and Culture

A large-scale description of men and women speaking-time in media is presented, based on the analysis of about 700.000 hours of French audiovisual documents, broadcasted from 2001 to 2018 on 22 TV channels and 21 radio stations. Speaking-time is desc

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::45bdf491917c7bbf0ab98bf8021f1cc9
http://publications.beeldengeluid.nl/pub/1728