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

TL;DR

This paper introduces a Siamese network-based verification system capable of attributing synthetic images to their generating architectures, including unknown ones, enhancing real-world applicability in open-set scenarios.

Contribution

It presents a novel verification framework that works in both closed and open-set conditions for synthetic image attribution to various architectures.

Findings

High accuracy in open-set synthetic image attribution

Effective across GANs, diffusion models, and transformers

Strong generalization to unseen architectures

Abstract

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.