Deceptive Beauty: Evaluating the Impact of Beauty Filters on Deepfake and Morphing Attack Detection

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Concas, Sara, La Cava, Simone Maurizio, Panzino, Andrea, Masala, Ester, Orrù, Giulia, Marcialis, Gian Luca
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914042903265280
author Concas, Sara
La Cava, Simone Maurizio
Panzino, Andrea
Masala, Ester
Orrù, Giulia
Marcialis, Gian Luca
author_facet Concas, Sara
La Cava, Simone Maurizio
Panzino, Andrea
Masala, Ester
Orrù, Giulia
Marcialis, Gian Luca
contents Digital beautification through social media filters has become increasingly popular, raising concerns about the reliability of facial images and videos and the effectiveness of automated face analysis. This issue is particularly critical for digital manipulation detectors, systems aiming at distinguishing between genuine and manipulated data, especially in cases involving deepfakes and morphing attacks designed to deceive humans and automated facial recognition. This study examines whether beauty filters impact the performance of deepfake and morphing attack detectors. We perform a comprehensive analysis, evaluating multiple state-of-the-art detectors on benchmark datasets before and after applying various smoothing filters. Our findings reveal performance degradation, highlighting vulnerabilities introduced by facial enhancements and underscoring the need for robust detection models resilient to such alterations.
format Preprint
id arxiv_https___arxiv_org_abs_2509_14120
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deceptive Beauty: Evaluating the Impact of Beauty Filters on Deepfake and Morphing Attack Detection
Concas, Sara
La Cava, Simone Maurizio
Panzino, Andrea
Masala, Ester
Orrù, Giulia
Marcialis, Gian Luca
Computer Vision and Pattern Recognition
Digital beautification through social media filters has become increasingly popular, raising concerns about the reliability of facial images and videos and the effectiveness of automated face analysis. This issue is particularly critical for digital manipulation detectors, systems aiming at distinguishing between genuine and manipulated data, especially in cases involving deepfakes and morphing attacks designed to deceive humans and automated facial recognition. This study examines whether beauty filters impact the performance of deepfake and morphing attack detectors. We perform a comprehensive analysis, evaluating multiple state-of-the-art detectors on benchmark datasets before and after applying various smoothing filters. Our findings reveal performance degradation, highlighting vulnerabilities introduced by facial enhancements and underscoring the need for robust detection models resilient to such alterations.
title Deceptive Beauty: Evaluating the Impact of Beauty Filters on Deepfake and Morphing Attack Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.14120