SFANet: Spatial-Frequency Attention Network for Deepfake Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912630677962752 |
|---|---|
| author | Ahire, Vrushank Muley, Aniruddh Zample, Shivam Verma, Siddharth Menon, Pranav Madan, Surbhi Dhall, Abhinav |
| author_facet | Ahire, Vrushank Muley, Aniruddh Zample, Shivam Verma, Siddharth Menon, Pranav Madan, Surbhi Dhall, Abhinav |
| contents | Detecting manipulated media has now become a pressing issue with the recent rise of deepfakes. Most existing approaches fail to generalize across diverse datasets and generation techniques. We thus propose a novel ensemble framework, combining the strengths of transformer-based architectures, such as Swin Transformers and ViTs, and texture-based methods, to achieve better detection accuracy and robustness. Our method introduces innovative data-splitting, sequential training, frequency splitting, patch-based attention, and face segmentation techniques to handle dataset imbalances, enhance high-impact regions (e.g., eyes and mouth), and improve generalization. Our model achieves state-of-the-art performance when tested on the DFWild-Cup dataset, a diverse subset of eight deepfake datasets. The ensemble benefits from the complementarity of these approaches, with transformers excelling in global feature extraction and texturebased methods providing interpretability. This work demonstrates that hybrid models can effectively address the evolving challenges of deepfake detection, offering a robust solution for real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04630 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SFANet: Spatial-Frequency Attention Network for Deepfake Detection Ahire, Vrushank Muley, Aniruddh Zample, Shivam Verma, Siddharth Menon, Pranav Madan, Surbhi Dhall, Abhinav Computer Vision and Pattern Recognition Artificial Intelligence Multimedia Detecting manipulated media has now become a pressing issue with the recent rise of deepfakes. Most existing approaches fail to generalize across diverse datasets and generation techniques. We thus propose a novel ensemble framework, combining the strengths of transformer-based architectures, such as Swin Transformers and ViTs, and texture-based methods, to achieve better detection accuracy and robustness. Our method introduces innovative data-splitting, sequential training, frequency splitting, patch-based attention, and face segmentation techniques to handle dataset imbalances, enhance high-impact regions (e.g., eyes and mouth), and improve generalization. Our model achieves state-of-the-art performance when tested on the DFWild-Cup dataset, a diverse subset of eight deepfake datasets. The ensemble benefits from the complementarity of these approaches, with transformers excelling in global feature extraction and texturebased methods providing interpretability. This work demonstrates that hybrid models can effectively address the evolving challenges of deepfake detection, offering a robust solution for real-world applications. |
| title | SFANet: Spatial-Frequency Attention Network for Deepfake Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Multimedia |
| url | https://arxiv.org/abs/2510.04630 |