IDEAW: Robust Neural Audio Watermarking with Invertible Dual-Embedding
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914960071720960 |
|---|---|
| author | Li, Pengcheng Zhang, Xulong Xiao, Jing Wang, Jianzong |
| author_facet | Li, Pengcheng Zhang, Xulong Xiao, Jing Wang, Jianzong |
| contents | The audio watermarking technique embeds messages into audio and accurately extracts messages from the watermarked audio. Traditional methods develop algorithms based on expert experience to embed watermarks into the time-domain or transform-domain of signals. With the development of deep neural networks, deep learning-based neural audio watermarking has emerged. Compared to traditional algorithms, neural audio watermarking achieves better robustness by considering various attacks during training. However, current neural watermarking methods suffer from low capacity and unsatisfactory imperceptibility. Additionally, the issue of watermark locating, which is extremely important and even more pronounced in neural audio watermarking, has not been adequately studied. In this paper, we design a dual-embedding watermarking model for efficient locating. We also consider the impact of the attack layer on the invertible neural network in robustness training, improving the model to enhance both its reasonableness and stability. Experiments show that the proposed model, IDEAW, can withstand various attacks with higher capacity and more efficient locating ability compared to existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_19627 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | IDEAW: Robust Neural Audio Watermarking with Invertible Dual-Embedding Li, Pengcheng Zhang, Xulong Xiao, Jing Wang, Jianzong Multimedia Cryptography and Security Sound Audio and Speech Processing K.6.5; D.4.6 The audio watermarking technique embeds messages into audio and accurately extracts messages from the watermarked audio. Traditional methods develop algorithms based on expert experience to embed watermarks into the time-domain or transform-domain of signals. With the development of deep neural networks, deep learning-based neural audio watermarking has emerged. Compared to traditional algorithms, neural audio watermarking achieves better robustness by considering various attacks during training. However, current neural watermarking methods suffer from low capacity and unsatisfactory imperceptibility. Additionally, the issue of watermark locating, which is extremely important and even more pronounced in neural audio watermarking, has not been adequately studied. In this paper, we design a dual-embedding watermarking model for efficient locating. We also consider the impact of the attack layer on the invertible neural network in robustness training, improving the model to enhance both its reasonableness and stability. Experiments show that the proposed model, IDEAW, can withstand various attacks with higher capacity and more efficient locating ability compared to existing methods. |
| title | IDEAW: Robust Neural Audio Watermarking with Invertible Dual-Embedding |
| topic | Multimedia Cryptography and Security Sound Audio and Speech Processing K.6.5; D.4.6 |
| url | https://arxiv.org/abs/2409.19627 |