Proceedings/Recueil Des Communications Année : 2025

FIDAVL: Fake Image Detection and Attribution Using Vision-Language Model

Résumé

We introduce FIDAVL: Fake Image Detection and Attribution using a Vision-Language Model. FIDAVL is a novel and efficient multitask approach inspired by the synergies between vision and language processing. Leveraging the benefits of zero-shot learning, FIDAVL exploits the complementarity between vision and language along with soft prompt-tuning strategy to detect fake images and accurately attribute them to their originating source models. We conducted extensive experiments on a comprehensive dataset comprising synthetic images generated by various state-of-the-art models. Our results demonstrate that FIDAVL achieves an encouraging average detection accuracy of 95.42% and F1-score of 95.47% while also obtaining noteworthy performance metrics, with an average F1-score of 92.64% and ROUGE-L score of 96.50% for attributing synthetic images to their respective source generation models. The source code of this work will be publicly released at https://github.com/Mamadou-Keita/FIDAVL.

Fichier non déposé

Dates et versions

hal-04856920 , version 1 (27-12-2024)

Identifiants

Citer

Mamadou Keita, Wassim Hamidouche, Hessen Bougueffa Eutamene, Abdelmalik Taleb-Ahmed, Abdenour Hadid. FIDAVL: Fake Image Detection and Attribution Using Vision-Language Model. International Conference on Pattern Recognition (ICPR 2024), 2025, Kolkata, India. 15321, pp.160-176, 2025, Included in the following conference series: International Conference on Pattern Recognition, ICPR 2024, ⟨10.1007/978-3-031-78305-0_11⟩. ⟨hal-04856920⟩
427 Consultations
0 Téléchargements

Altmetric

Partager

  • More