FIDAVL: Fake Image Detection and Attribution using Vision-Language Model
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929487232368640 |
|---|---|
| author | Keita, Mamadou Hamidouche, Wassim Eutamene, Hessen Bougueffa Taleb-Ahmed, Abdelmalik Hadid, Abdenour |
| author_facet | Keita, Mamadou Hamidouche, Wassim Eutamene, Hessen Bougueffa Taleb-Ahmed, Abdelmalik Hadid, Abdenour |
| contents | We introduce FIDAVL: Fake Image Detection and Attribution using a Vision-Language Model. FIDAVL is a novel and efficient mul-titask 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_03109 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FIDAVL: Fake Image Detection and Attribution using Vision-Language Model Keita, Mamadou Hamidouche, Wassim Eutamene, Hessen Bougueffa Taleb-Ahmed, Abdelmalik Hadid, Abdenour Computer Vision and Pattern Recognition Cryptography and Security We introduce FIDAVL: Fake Image Detection and Attribution using a Vision-Language Model. FIDAVL is a novel and efficient mul-titask 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. |
| title | FIDAVL: Fake Image Detection and Attribution using Vision-Language Model |
| topic | Computer Vision and Pattern Recognition Cryptography and Security |
| url | https://arxiv.org/abs/2409.03109 |