Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution
This addresses the need to prevent misuse of generated images by enabling model-agnostic attribution, though it is incremental as it builds on existing CLIP technology.
The paper tackles the problem of identifying which generative model produced an image, using only a few example images from the source model without access to the model itself, and proposes OCC-CLIP, a framework that achieves effective origin attribution across various models, including verification with DALL-E 3 API.
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.