A Siamese-based Verification System for Open-set Architecture Attribution of Synthetic Images

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Abady, Lydia, Wang, Jun, Tondi, Benedetta, Barni, Mauro
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929194767745024
author Abady, Lydia
Wang, Jun
Tondi, Benedetta
Barni, Mauro
author_facet Abady, Lydia
Wang, Jun
Tondi, Benedetta
Barni, Mauro
contents Despite the wide variety of methods developed for synthetic image attribution, most of them can only attribute images generated by models or architectures included in the training set and do not work with unknown architectures, hindering their applicability in real-world scenarios. In this paper, we propose a verification framework that relies on a Siamese Network to address the problem of open-set attribution of synthetic images to the architecture that generated them. We consider two different settings. In the first setting, the system determines whether two images have been produced by the same generative architecture or not. In the second setting, the system verifies a claim about the architecture used to generate a synthetic image, utilizing one or multiple reference images generated by the claimed architecture. The main strength of the proposed system is its ability to operate in both closed and open-set scenarios so that the input images, either the query and reference images, can belong to the architectures considered during training or not. Experimental evaluations encompassing various generative architectures such as GANs, diffusion models, and transformers, focusing on synthetic face image generation, confirm the excellent performance of our method in both closed and open-set settings, as well as its strong generalization capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2307_09822
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Siamese-based Verification System for Open-set Architecture Attribution of Synthetic Images
Abady, Lydia
Wang, Jun
Tondi, Benedetta
Barni, Mauro
Computer Vision and Pattern Recognition
Despite the wide variety of methods developed for synthetic image attribution, most of them can only attribute images generated by models or architectures included in the training set and do not work with unknown architectures, hindering their applicability in real-world scenarios. In this paper, we propose a verification framework that relies on a Siamese Network to address the problem of open-set attribution of synthetic images to the architecture that generated them. We consider two different settings. In the first setting, the system determines whether two images have been produced by the same generative architecture or not. In the second setting, the system verifies a claim about the architecture used to generate a synthetic image, utilizing one or multiple reference images generated by the claimed architecture. The main strength of the proposed system is its ability to operate in both closed and open-set scenarios so that the input images, either the query and reference images, can belong to the architectures considered during training or not. Experimental evaluations encompassing various generative architectures such as GANs, diffusion models, and transformers, focusing on synthetic face image generation, confirm the excellent performance of our method in both closed and open-set settings, as well as its strong generalization capabilities.
title A Siamese-based Verification System for Open-set Architecture Attribution of Synthetic Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2307.09822