Detecting AutoEncoder is Enough to Catch LDM Generated Images
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_ | 1866910692918951936 |
|---|---|
| author | Vesnin, Dmitry Levshun, Dmitry Chechulin, Andrey |
| author_facet | Vesnin, Dmitry Levshun, Dmitry Chechulin, Andrey |
| contents | In recent years, diffusion models have become one of the main methods for generating images. However, detecting images generated by these models remains a challenging task. This paper proposes a novel method for detecting images generated by Latent Diffusion Models (LDM) by identifying artifacts introduced by their autoencoders. By training a detector to distinguish between real images and those reconstructed by the LDM autoencoder, the method enables detection of generated images without directly training on them. The novelty of this research lies in the fact that, unlike similar approaches, this method does not require training on synthesized data, significantly reducing computational costs and enhancing generalization ability. Experimental results show high detection accuracy with minimal false positives, making this approach a promising tool for combating fake images. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_06441 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Detecting AutoEncoder is Enough to Catch LDM Generated Images Vesnin, Dmitry Levshun, Dmitry Chechulin, Andrey Computer Vision and Pattern Recognition Cryptography and Security Machine Learning In recent years, diffusion models have become one of the main methods for generating images. However, detecting images generated by these models remains a challenging task. This paper proposes a novel method for detecting images generated by Latent Diffusion Models (LDM) by identifying artifacts introduced by their autoencoders. By training a detector to distinguish between real images and those reconstructed by the LDM autoencoder, the method enables detection of generated images without directly training on them. The novelty of this research lies in the fact that, unlike similar approaches, this method does not require training on synthesized data, significantly reducing computational costs and enhancing generalization ability. Experimental results show high detection accuracy with minimal false positives, making this approach a promising tool for combating fake images. |
| title | Detecting AutoEncoder is Enough to Catch LDM Generated Images |
| topic | Computer Vision and Pattern Recognition Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2411.06441 |