Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2410.07436 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916431473410048 |
|---|---|
| author | Channing, Georgia Sock, Juil Clark, Ronald Torr, Philip de Witt, Christian Schroeder |
| author_facet | Channing, Georgia Sock, Juil Clark, Ronald Torr, Philip de Witt, Christian Schroeder |
| contents | The rapid proliferation of AI-manipulated or generated audio deepfakes poses serious challenges to media integrity and election security. Current AI-driven detection solutions lack explainability and underperform in real-world settings. In this paper, we introduce novel explainability methods for state-of-the-art transformer-based audio deepfake detectors and open-source a novel benchmark for real-world generalizability. By narrowing the explainability gap between transformer-based audio deepfake detectors and traditional methods, our results not only build trust with human experts, but also pave the way for unlocking the potential of citizen intelligence to overcome the scalability issue in audio deepfake detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_07436 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap Channing, Georgia Sock, Juil Clark, Ronald Torr, Philip de Witt, Christian Schroeder Machine Learning Sound Audio and Speech Processing The rapid proliferation of AI-manipulated or generated audio deepfakes poses serious challenges to media integrity and election security. Current AI-driven detection solutions lack explainability and underperform in real-world settings. In this paper, we introduce novel explainability methods for state-of-the-art transformer-based audio deepfake detectors and open-source a novel benchmark for real-world generalizability. By narrowing the explainability gap between transformer-based audio deepfake detectors and traditional methods, our results not only build trust with human experts, but also pave the way for unlocking the potential of citizen intelligence to overcome the scalability issue in audio deepfake detection. |
| title | Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap |
| topic | Machine Learning Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2410.07436 |