Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasets
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916181817950208 |
|---|---|
| author | Grommelt, Patrick Weiss, Louis Pfreundt, Franz-Josef Keuper, Janis |
| author_facet | Grommelt, Patrick Weiss, Louis Pfreundt, Franz-Josef Keuper, Janis |
| contents | The widespread adoption of generative image models has highlighted the urgent need to detect artificial content, which is a crucial step in combating widespread manipulation and misinformation. Consequently, numerous detectors and associated datasets have emerged. However, many of these datasets inadvertently introduce undesirable biases, thereby impacting the effectiveness and evaluation of detectors. In this paper, we emphasize that many datasets for AI-generated image detection contain biases related to JPEG compression and image size. Using the GenImage dataset, we demonstrate that detectors indeed learn from these undesired factors. Furthermore, we show that removing the named biases substantially increases robustness to JPEG compression and significantly alters the cross-generator performance of evaluated detectors. Specifically, it leads to more than 11 percentage points increase in cross-generator performance for ResNet50 and Swin-T detectors on the GenImage dataset, achieving state-of-the-art results.
We provide the dataset and source codes of this paper on the anonymous website: https://www.unbiased-genimage.org |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_17608 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasets Grommelt, Patrick Weiss, Louis Pfreundt, Franz-Josef Keuper, Janis Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning The widespread adoption of generative image models has highlighted the urgent need to detect artificial content, which is a crucial step in combating widespread manipulation and misinformation. Consequently, numerous detectors and associated datasets have emerged. However, many of these datasets inadvertently introduce undesirable biases, thereby impacting the effectiveness and evaluation of detectors. In this paper, we emphasize that many datasets for AI-generated image detection contain biases related to JPEG compression and image size. Using the GenImage dataset, we demonstrate that detectors indeed learn from these undesired factors. Furthermore, we show that removing the named biases substantially increases robustness to JPEG compression and significantly alters the cross-generator performance of evaluated detectors. Specifically, it leads to more than 11 percentage points increase in cross-generator performance for ResNet50 and Swin-T detectors on the GenImage dataset, achieving state-of-the-art results. We provide the dataset and source codes of this paper on the anonymous website: https://www.unbiased-genimage.org |
| title | Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasets |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2403.17608 |