Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Fengyuan, Luo, Haochen, Li, Yiming, Torr, Philip, Gu, Jindong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909261282410496
author Liu, Fengyuan
Luo, Haochen
Li, Yiming
Torr, Philip
Gu, Jindong
author_facet Liu, Fengyuan
Luo, Haochen
Li, Yiming
Torr, Philip
Gu, Jindong
contents Recent progress in visual generative models enables the generation of high-quality images. To prevent the misuse of generated images, it is important to identify the origin model that generates them. In this work, we study the origin attribution of generated images in a practical setting where only a few images generated by a source model are available and the source model cannot be accessed. The goal is to check if a given image is generated by the source model. We first formulate this problem as a few-shot one-class classification task. To solve the task, we propose OCC-CLIP, a CLIP-based framework for few-shot one-class classification, enabling the identification of an image's source model, even among multiple candidates. Extensive experiments corresponding to various generative models verify the effectiveness of our OCC-CLIP framework. Furthermore, an experiment based on the recently released DALL-E 3 API verifies the real-world applicability of our solution.
format Preprint
id arxiv_https___arxiv_org_abs_2404_02697
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution
Liu, Fengyuan
Luo, Haochen
Li, Yiming
Torr, Philip
Gu, Jindong
Computer Vision and Pattern Recognition
Recent progress in visual generative models enables the generation of high-quality images. To prevent the misuse of generated images, it is important to identify the origin model that generates them. In this work, we study the origin attribution of generated images in a practical setting where only a few images generated by a source model are available and the source model cannot be accessed. The goal is to check if a given image is generated by the source model. We first formulate this problem as a few-shot one-class classification task. To solve the task, we propose OCC-CLIP, a CLIP-based framework for few-shot one-class classification, enabling the identification of an image's source model, even among multiple candidates. Extensive experiments corresponding to various generative models verify the effectiveness of our OCC-CLIP framework. Furthermore, an experiment based on the recently released DALL-E 3 API verifies the real-world applicability of our solution.
title Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.02697