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

by   Lydia Abady, et al.

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.


Open Set Synthetic Image Source Attribution

AI-generated images have become increasingly realistic and have garnered...

Progressive Open Space Expansion for Open-Set Model Attribution

Despite the remarkable progress in generative technology, the Janus-face...

Simple U-net Based Synthetic Polyp Image Generation: Polyp to Negative and Negative to Polyp

Synthetic polyp generation is a good alternative to overcome the privacy...

Evaluating Data Attribution for Text-to-Image Models

While large text-to-image models are able to synthesize "novel" images, ...

Open Set Classification of GAN-based Image Manipulations via a ViT-based Hybrid Architecture

Classification of AI-manipulated content is receiving great attention, f...

Source Generator Attribution via Inversion

With advances in Generative Adversarial Networks (GANs) leading to drama...

Towards Discovery and Attribution of Open-world GAN Generated Images

With the recent progress in Generative Adversarial Networks (GANs), it i...

Please sign up or login with your details

Forgot password? Click here to reset