Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixture
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_ | 1866915816841150464 |
|---|---|
| author | Kong, Chenqi Luo, Anwei Bao, Peijun Li, Haoliang Wan, Renjie Zheng, Zengwei Rocha, Anderson Kot, Alex C. |
| author_facet | Kong, Chenqi Luo, Anwei Bao, Peijun Li, Haoliang Wan, Renjie Zheng, Zengwei Rocha, Anderson Kot, Alex C. |
| contents | Open-set face forgery detection poses significant security threats and presents substantial challenges for existing detection models. These detectors primarily have two limitations: they cannot generalize across unknown forgery domains and inefficiently adapt to new data. To address these issues, we introduce an approach that is both general and parameter-efficient for face forgery detection. It builds on the assumption that different forgery source domains exhibit distinct style statistics. Previous methods typically require fully fine-tuning pre-trained networks, consuming substantial time and computational resources. In turn, we design a forgery-style mixture formulation that augments the diversity of forgery source domains, enhancing the model's generalizability across unseen domains. Drawing on recent advancements in vision transformers (ViT) for face forgery detection, we develop a parameter-efficient ViT-based detection model that includes lightweight forgery feature extraction modules and enables the model to extract global and local forgery clues simultaneously. We only optimize the inserted lightweight modules during training, maintaining the original ViT structure with its pre-trained ImageNet weights. This training strategy effectively preserves the informative pre-trained knowledge while flexibly adapting the model to the task of Deepfake detection. Extensive experimental results demonstrate that the designed model achieves state-of-the-art generalizability with significantly reduced trainable parameters, representing an important step toward open-set Deepfake detection in the wild. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_12791 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixture Kong, Chenqi Luo, Anwei Bao, Peijun Li, Haoliang Wan, Renjie Zheng, Zengwei Rocha, Anderson Kot, Alex C. Computer Vision and Pattern Recognition Open-set face forgery detection poses significant security threats and presents substantial challenges for existing detection models. These detectors primarily have two limitations: they cannot generalize across unknown forgery domains and inefficiently adapt to new data. To address these issues, we introduce an approach that is both general and parameter-efficient for face forgery detection. It builds on the assumption that different forgery source domains exhibit distinct style statistics. Previous methods typically require fully fine-tuning pre-trained networks, consuming substantial time and computational resources. In turn, we design a forgery-style mixture formulation that augments the diversity of forgery source domains, enhancing the model's generalizability across unseen domains. Drawing on recent advancements in vision transformers (ViT) for face forgery detection, we develop a parameter-efficient ViT-based detection model that includes lightweight forgery feature extraction modules and enables the model to extract global and local forgery clues simultaneously. We only optimize the inserted lightweight modules during training, maintaining the original ViT structure with its pre-trained ImageNet weights. This training strategy effectively preserves the informative pre-trained knowledge while flexibly adapting the model to the task of Deepfake detection. Extensive experimental results demonstrate that the designed model achieves state-of-the-art generalizability with significantly reduced trainable parameters, representing an important step toward open-set Deepfake detection in the wild. |
| title | Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixture |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.12791 |