Audio-Visual Deepfake Detection With Local Temporal Inconsistencies
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913734322028544 |
|---|---|
| author | Astrid, Marcella Ghorbel, Enjie Aouada, Djamila |
| author_facet | Astrid, Marcella Ghorbel, Enjie Aouada, Djamila |
| contents | This paper proposes an audio-visual deepfake detection approach that aims to capture fine-grained temporal inconsistencies between audio and visual modalities. To achieve this, both architectural and data synthesis strategies are introduced. From an architectural perspective, a temporal distance map, coupled with an attention mechanism, is designed to capture these inconsistencies while minimizing the impact of irrelevant temporal subsequences. Moreover, we explore novel pseudo-fake generation techniques to synthesize local inconsistencies. Our approach is evaluated against state-of-the-art methods using the DFDC and FakeAVCeleb datasets, demonstrating its effectiveness in detecting audio-visual deepfakes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_08137 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Audio-Visual Deepfake Detection With Local Temporal Inconsistencies Astrid, Marcella Ghorbel, Enjie Aouada, Djamila Computer Vision and Pattern Recognition Cryptography and Security Multimedia Sound Audio and Speech Processing This paper proposes an audio-visual deepfake detection approach that aims to capture fine-grained temporal inconsistencies between audio and visual modalities. To achieve this, both architectural and data synthesis strategies are introduced. From an architectural perspective, a temporal distance map, coupled with an attention mechanism, is designed to capture these inconsistencies while minimizing the impact of irrelevant temporal subsequences. Moreover, we explore novel pseudo-fake generation techniques to synthesize local inconsistencies. Our approach is evaluated against state-of-the-art methods using the DFDC and FakeAVCeleb datasets, demonstrating its effectiveness in detecting audio-visual deepfakes. |
| title | Audio-Visual Deepfake Detection With Local Temporal Inconsistencies |
| topic | Computer Vision and Pattern Recognition Cryptography and Security Multimedia Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2501.08137 |