OmniDFA: A Unified Framework for Open Set Synthesis Image Detection and Few-Shot Attribution

ICLR 2026 Conference Submission19589 Authors

Keywords: Deepfake Detection, Synthetic Image Detection, Few-Shot Learning, Image Attribution

TL;DR: This paper propose a large-scale synthetic image datasets and a novel deepfake detector.

Abstract:

AI-generated image (AIGI) detection and source model attribution remain central challenges in combating deepfake abuses, primarily due to the structural diversity of generative models.
Current detection methods are prone to overfitting specific forgery traits, whereas source attribution offers a robust alternative through fine-grained feature discrimination.
However, synthetic image attribution remains constrained by the scarcity of large-scale, well-categorized synthetic datasets, limiting its practicality and compatibility with detection systems.
In this work, we propose a new paradigm for image attribution called open-set, few-shot source identification.
This paradigm is designed to reliably identify unseen generators using only limited samples, making it highly suitable for real-world application.
To this end, we introduce OmniDFA (Omni Detector and Few-shot Attributor), a novel framework for AIGI that not only assesses the authenticity of images, but also determines the synthesis origins in a few-shot manner.
To facilitate this work, we construct OmniFake, a large class-aware synthetic image dataset that curates $1.17$ M images from $45$ distinct generative models, substantially enriching the foundational resources for research on both AIGI detection and attribution.
Experiments demonstrate that OmniDFA exhibits excellent capability in open-set attribution and achieves state-of-the-art generalization performance on AIGI detection.
The integration of the new task enhances detection performance and offers an efficient and scalable path toward practical adoption.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 19589