Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.09314 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911267234512896 |
|---|---|
| author | Li, Xinghan Yu, Yue Song, Xue Shan, Haijun Chen, Jingjing |
| author_facet | Li, Xinghan Yu, Yue Song, Xue Shan, Haijun Chen, Jingjing |
| contents | With the rapid advancement of vision generation models, the potential security risks stemming from synthetic visual content have garnered increasing attention, posing significant challenges for AI-generated image detection. Existing methods suffer from inadequate generalization capabilities, resulting in unsatisfactory performance on emerging generative models. To address this issue, this paper presents NIRNet (Noise-based Imprint Revealing Network), a novel framework that leverages noise-based imprint for the detection task. Specifically, we propose a novel Noise-based Imprint Simulator to capture intrinsic patterns imprinted in images generated by different models. By aggregating imprint from various generative models, imprint of future models can be extrapolated to expand training data, thereby enhancing generalization and robustness. Furthermore, we design a new pipeline that pioneers the use of noise patterns, derived from a Noise-based Imprint Extractor, alongside other visual features for AI-generated image detection, significantly improving detection performance. Our approach achieves state-of-the-art performance across seven diverse benchmarks, including five public datasets and two newly proposed generalization tests, demonstrating its superior generalization and effectiveness.
Paper Submission: pdf |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_09314 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Revealing the Implicit Noise-based Imprint of Generative Models Li, Xinghan Yu, Yue Song, Xue Shan, Haijun Chen, Jingjing Computer Vision and Pattern Recognition With the rapid advancement of vision generation models, the potential security risks stemming from synthetic visual content have garnered increasing attention, posing significant challenges for AI-generated image detection. Existing methods suffer from inadequate generalization capabilities, resulting in unsatisfactory performance on emerging generative models. To address this issue, this paper presents NIRNet (Noise-based Imprint Revealing Network), a novel framework that leverages noise-based imprint for the detection task. Specifically, we propose a novel Noise-based Imprint Simulator to capture intrinsic patterns imprinted in images generated by different models. By aggregating imprint from various generative models, imprint of future models can be extrapolated to expand training data, thereby enhancing generalization and robustness. Furthermore, we design a new pipeline that pioneers the use of noise patterns, derived from a Noise-based Imprint Extractor, alongside other visual features for AI-generated image detection, significantly improving detection performance. Our approach achieves state-of-the-art performance across seven diverse benchmarks, including five public datasets and two newly proposed generalization tests, demonstrating its superior generalization and effectiveness. Paper Submission: pdf |
| title | Revealing the Implicit Noise-based Imprint of Generative Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.09314 |