FakeMark: Deepfake Speech Attribution With Watermarked Artifacts
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918160759783424 |
|---|---|
| author | Ge, Wanying Wang, Xin Yamagishi, Junichi |
| author_facet | Ge, Wanying Wang, Xin Yamagishi, Junichi |
| contents | Deepfake speech attribution remains challenging for existing solutions. Classifier-based solutions often fail to generalize to domain-shifted samples, and watermarking-based solutions are easily compromised by distortions like codec compression or malicious removal attacks. To address these issues, we propose FakeMark, a novel watermarking framework that injects artifact-correlated watermarks associated with deepfake systems rather than pre-assigned bitstring messages. This design allows a detector to attribute the source system by leveraging both injected watermark and intrinsic deepfake artifacts, remaining effective even if one of these cues is elusive or removed. Experimental results show that FakeMark improves generalization to cross-dataset samples where classifier-based solutions struggle and maintains high accuracy under various distortions where conventional watermarking-based solutions fail. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_12042 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FakeMark: Deepfake Speech Attribution With Watermarked Artifacts Ge, Wanying Wang, Xin Yamagishi, Junichi Audio and Speech Processing Deepfake speech attribution remains challenging for existing solutions. Classifier-based solutions often fail to generalize to domain-shifted samples, and watermarking-based solutions are easily compromised by distortions like codec compression or malicious removal attacks. To address these issues, we propose FakeMark, a novel watermarking framework that injects artifact-correlated watermarks associated with deepfake systems rather than pre-assigned bitstring messages. This design allows a detector to attribute the source system by leveraging both injected watermark and intrinsic deepfake artifacts, remaining effective even if one of these cues is elusive or removed. Experimental results show that FakeMark improves generalization to cross-dataset samples where classifier-based solutions struggle and maintains high accuracy under various distortions where conventional watermarking-based solutions fail. |
| title | FakeMark: Deepfake Speech Attribution With Watermarked Artifacts |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2510.12042 |