A Case Study on How Beautification Filters Can Fool Deepfake Detectors - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

A Case Study on How Beautification Filters Can Fool Deepfake Detectors

Alexandre Libourel
  • Fonction : Auteur
  • PersonId : 1365967
Sahar Husseini
  • Fonction : Auteur
  • PersonId : 1365968
Jean-Luc Dugelay
  • Fonction : Auteur
  • PersonId : 1016456

Résumé

If telling the difference between a real video and a deepfake is difficult, with the proliferation of beautification filters on social networks it becomes nearly impossible to differentiate between a real video, a video enhanced by a filter, and a video with its original identity replaced. Therefore, is it possible to fool state-of-the-art (SotA) detectors by simply applying a beautification filter to the manipulated video? In this paper, we study the impact of beautification filters on Celeb-DF-B, a novel database created by applying popular social media beautification filters to a subset of real and fake videos from the Celeb-DF dataset. We assessed three SotA passive deepfake detectors, comparing their performance against that of human evaluators. The results indicate that filters significantly alter the behavior of the three detectors studied, resulting in a notable decrease in the video-level AUC when classifying beautified videos. In the context of human-level performance, the use of filters similarly influences human decision-making, affecting the accurate categorization of videos as either real or fake.
Fichier principal
Vignette du fichier
IWBF.pdf (736.64 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04514781 , version 1 (21-03-2024)

Identifiants

  • HAL Id : hal-04514781 , version 1

Citer

Alexandre Libourel, Sahar Husseini, Nelida Mirabet-Herranz, Jean-Luc Dugelay. A Case Study on How Beautification Filters Can Fool Deepfake Detectors. IWBF 2024, 12th IEEE International Workshop on Biometrics and Forensics, IEEE, Apr 2024, Twente, Netherlands. ⟨hal-04514781⟩

Collections

EURECOM ANR
28 Consultations
25 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More