EIRES:Training-free AI-Generated Image Detection via Edit-Induced Reconstruction Error Shift
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909971562627072 |
|---|---|
| author | Jiang, Wan Yan, Jing Chen, Xiaojing Shen, Lin Lin, Chenhao Diao, Yunfeng Hong, Richang |
| author_facet | Jiang, Wan Yan, Jing Chen, Xiaojing Shen, Lin Lin, Chenhao Diao, Yunfeng Hong, Richang |
| contents | Diffusion models have recently achieved remarkable photorealism, making it increasingly difficult to distinguish real images from generated ones, raising significant privacy and security concerns. In response, we present a key finding: structural edits enhance the reconstruction of real images while degrading that of generated images, creating a distinctive edit-induced reconstruction error shift. This asymmetric shift enhances the separability between real and generated images. Building on this insight, we propose EIRES, a training-free method that leverages structural edits to reveal inherent differences between real and generated images. To explain the discriminative power of this shift, we derive the reconstruction error lower bound under edit perturbations. Since EIRES requires no training, thresholding depends solely on the natural separability of the signal, where a larger margin yields more reliable detection. Extensive experiments show that EIRES is effective across diverse generative models and remains robust on the unbiased subset, even under post-processing operations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_25141 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EIRES:Training-free AI-Generated Image Detection via Edit-Induced Reconstruction Error Shift Jiang, Wan Yan, Jing Chen, Xiaojing Shen, Lin Lin, Chenhao Diao, Yunfeng Hong, Richang Computer Vision and Pattern Recognition Diffusion models have recently achieved remarkable photorealism, making it increasingly difficult to distinguish real images from generated ones, raising significant privacy and security concerns. In response, we present a key finding: structural edits enhance the reconstruction of real images while degrading that of generated images, creating a distinctive edit-induced reconstruction error shift. This asymmetric shift enhances the separability between real and generated images. Building on this insight, we propose EIRES, a training-free method that leverages structural edits to reveal inherent differences between real and generated images. To explain the discriminative power of this shift, we derive the reconstruction error lower bound under edit perturbations. Since EIRES requires no training, thresholding depends solely on the natural separability of the signal, where a larger margin yields more reliable detection. Extensive experiments show that EIRES is effective across diverse generative models and remains robust on the unbiased subset, even under post-processing operations. |
| title | EIRES:Training-free AI-Generated Image Detection via Edit-Induced Reconstruction Error Shift |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.25141 |