Diffusion Facial Forgery Detection
This addresses the social risk of facial forgeries, which are less explored than general diffusion-generated images, but the approach is incremental as it builds on existing detection methods with a new dataset and regularization technique.
The paper tackles the problem of detecting diffusion-generated facial forgeries by introducing DiFF, a dataset of over 500,000 images synthesized with 13 methods, and finds that both human and automated detection accuracy often falls below 30%.
Detecting diffusion-generated images has recently grown into an emerging research area. Existing diffusion-based datasets predominantly focus on general image generation. However, facial forgeries, which pose a more severe social risk, have remained less explored thus far. To address this gap, this paper introduces DiFF, a comprehensive dataset dedicated to face-focused diffusion-generated images. DiFF comprises over 500,000 images that are synthesized using thirteen distinct generation methods under four conditions. In particular, this dataset leverages 30,000 carefully collected textual and visual prompts, ensuring the synthesis of images with both high fidelity and semantic consistency. We conduct extensive experiments on the DiFF dataset via a human test and several representative forgery detection methods. The results demonstrate that the binary detection accuracy of both human observers and automated detectors often falls below 30%, shedding light on the challenges in detecting diffusion-generated facial forgeries. Furthermore, we propose an edge graph regularization approach to effectively enhance the generalization capability of existing detectors.