Rethinking Cross-Generator Image Forgery Detection through DINOv3
This work addresses the challenge of detecting forgeries across diverse generative models, offering an efficient baseline for researchers and practitioners, though it is incremental in leveraging existing foundation models.
The paper tackled the problem of cross-generator image forgery detection, where existing methods fail on unseen generators, and found that frozen DINOv3 models already show strong detection capability without fine-tuning, achieving improved accuracy across datasets with a simple token-ranking strategy.
As generative models become increasingly diverse and powerful, cross-generator detection has emerged as a new challenge. Existing detection methods often memorize artifacts of specific generative models rather than learning transferable cues, leading to substantial failures on unseen generators. Surprisingly, this work finds that frozen visual foundation models, especially DINOv3, already exhibit strong cross-generator detection capability without any fine-tuning. Through systematic studies on frequency, spatial, and token perspectives, we observe that DINOv3 tends to rely on global, low-frequency structures as weak but transferable authenticity cues instead of high-frequency, generator-specific artifacts. Motivated by this insight, we introduce a simple, training-free token-ranking strategy followed by a lightweight linear probe to select a small subset of authenticity-relevant tokens. This token subset consistently improves detection accuracy across all evaluated datasets. Our study provides empirical evidence and a feasible hypothesis for understanding why foundation models generalize across diverse generators, offering a universal, efficient, and interpretable baseline for image forgery detection.