Generalized Design Choices for Deepfake Detectors
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915639377002496 |
|---|---|
| author | Pellegrini, Lorenzo Pandolfini, Serafino Maltoni, Davide Ferrara, Matteo Prati, Marco Ramilli, Marco |
| author_facet | Pellegrini, Lorenzo Pandolfini, Serafino Maltoni, Davide Ferrara, Matteo Prati, Marco Ramilli, Marco |
| contents | The effectiveness of deepfake detection methods often depends less on their core design and more on implementation details such as data preprocessing, augmentation strategies, and optimization techniques. These factors make it difficult to fairly compare detectors and to understand which factors truly contribute to their performance. To address this, we systematically investigate how different design choices influence the accuracy and generalization capabilities of deepfake detection models, focusing on aspects related to training, inference, and incremental updates. By isolating the impact of individual factors, we aim to establish robust, architecture-agnostic best practices for the design and development of future deepfake detection systems. Our experiments identify a set of design choices that consistently improve deepfake detection and enable state-of-the-art performance on the AI-GenBench benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_21507 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Generalized Design Choices for Deepfake Detectors Pellegrini, Lorenzo Pandolfini, Serafino Maltoni, Davide Ferrara, Matteo Prati, Marco Ramilli, Marco Computer Vision and Pattern Recognition The effectiveness of deepfake detection methods often depends less on their core design and more on implementation details such as data preprocessing, augmentation strategies, and optimization techniques. These factors make it difficult to fairly compare detectors and to understand which factors truly contribute to their performance. To address this, we systematically investigate how different design choices influence the accuracy and generalization capabilities of deepfake detection models, focusing on aspects related to training, inference, and incremental updates. By isolating the impact of individual factors, we aim to establish robust, architecture-agnostic best practices for the design and development of future deepfake detection systems. Our experiments identify a set of design choices that consistently improve deepfake detection and enable state-of-the-art performance on the AI-GenBench benchmark. |
| title | Generalized Design Choices for Deepfake Detectors |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.21507 |