Targeted Augmented Data for Audio Deepfake Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911951045525504 |
|---|---|
| author | Astrid, Marcella Ghorbel, Enjie Aouada, Djamila |
| author_facet | Astrid, Marcella Ghorbel, Enjie Aouada, Djamila |
| contents | The availability of highly convincing audio deepfake generators highlights the need for designing robust audio deepfake detectors. Existing works often rely solely on real and fake data available in the training set, which may lead to overfitting, thereby reducing the robustness to unseen manipulations. To enhance the generalization capabilities of audio deepfake detectors, we propose a novel augmentation method for generating audio pseudo-fakes targeting the decision boundary of the model. Inspired by adversarial attacks, we perturb original real data to synthesize pseudo-fakes with ambiguous prediction probabilities. Comprehensive experiments on two well-known architectures demonstrate that the proposed augmentation contributes to improving the generalization capabilities of these architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_07598 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Targeted Augmented Data for Audio Deepfake Detection Astrid, Marcella Ghorbel, Enjie Aouada, Djamila Sound Machine Learning Audio and Speech Processing The availability of highly convincing audio deepfake generators highlights the need for designing robust audio deepfake detectors. Existing works often rely solely on real and fake data available in the training set, which may lead to overfitting, thereby reducing the robustness to unseen manipulations. To enhance the generalization capabilities of audio deepfake detectors, we propose a novel augmentation method for generating audio pseudo-fakes targeting the decision boundary of the model. Inspired by adversarial attacks, we perturb original real data to synthesize pseudo-fakes with ambiguous prediction probabilities. Comprehensive experiments on two well-known architectures demonstrate that the proposed augmentation contributes to improving the generalization capabilities of these architectures. |
| title | Targeted Augmented Data for Audio Deepfake Detection |
| topic | Sound Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2407.07598 |