Spaces:
Sleeping
Sleeping
|
Download detectors/NPR/README.md from Truebees/DeepShield-Detectors: direct link, hf CLI and curl.
- Browser
- Download file 2.45 kB
-
https://huggingface.co/spaces/Truebees/DeepShield-Detectors/resolve/main/detectors/NPR/README.md
- Command line
-
hf download hf://spaces/Truebees/DeepShield-Detectors/detectors/NPR/README.md
-
curl -L -o README.md https://huggingface.co/spaces/Truebees/DeepShield-Detectors/resolve/main/detectors/NPR/README.md
2.45 kB
| # Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection | |
| [](https://github.com/chuangchuangtan/NPR-DeepfakeDetection) | |
| [](https://arxiv.org/abs/2312.10461) | |
| Original Paper: | |
| [Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection](https://arxiv.org/abs/2312.10461). | |
| Authors: Chuangchuang Tan, Huan Liu, Yao Zhao, Shikui Wei, Guanghua Gu, Ping Liu, Yunchao Wei. | |
| ## Abstract | |
| Recently, the proliferation of highly realistic synthetic | |
| images, facilitated through a variety of GANs and Diffu- | |
| sions, has significantly heightened the susceptibility to mis- | |
| use. While the primary focus of deepfake detection has tra- | |
| ditionally centered on the design of detection algorithms, | |
| an investigative inquiry into the generator architectures has | |
| remained conspicuously absent in recent years. This paper | |
| contributes to this lacuna by rethinking the architectures of | |
| CNN-based generator, thereby establishing a generalized | |
| representation of synthetic artifacts. Our findings illumi- | |
| nate that the up-sampling operator can, beyond frequency- | |
| based artifacts, produce generalized forgery artifacts. In | |
| particular, the local interdependence among image pixels | |
| caused by upsampling operators is significantly demon- | |
| strated in synthetic images generated by GAN or diffusion. | |
| Building upon this observation, we introduce the concept of | |
| Neighboring Pixel Relationships(NPR) as a means to cap- | |
| ture and characterize the generalized structural artifacts | |
| stemming from up-sampling operations. A comprehensive | |
| analysis is conducted on an open-world dataset, comprising | |
| samples generated by 28 distinct generative models. This | |
| analysis culminates in the establishment of a novel state-of- | |
| the-art performance, showcasing a remarkable 11.6% im- | |
| provement over existing methods | |
| ## Please Cite | |
| ``` | |
| @inproceedings{tan2024rethinking, | |
| title={Rethinking the up-sampling operations in cnn-based generative network for generalizable deepfake detection}, | |
| author={Tan, Chuangchuang and Zhao, Yao and Wei, Shikui and Gu, Guanghua and Liu, Ping and Wei, Yunchao}, | |
| booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, | |
| pages={28130--28139}, | |
| year={2024} | |
| } | |
| ``` |