This record contains the preprint version of a survey manuscript on source attribution of AI-generated images. The manuscript reviews existing approaches for tracing synthetic images back to their generative sources, with a focus on passive attribution methods. It organizes the literature under a unified conceptual framework, covering different attribution scenarios, methodological paradigms, attribution granularities, open-set settings, commonly used datasets, and remaining challenges in the field. PS: This version has not yet undergone formal journal peer review. The final published version, if accepted, may differ from this preprint.
Li et al. (Tue,) studied this question.