TriniMark: A Robust Generative Speech Watermarking Method for Trinity-Level Attribution
By: Yue Li, Weizhi Liu, Dongdong Lin
Potential Business Impact:
Marks fake voices so creators keep their work.
The emergence of diffusion models has facilitated the generation of speech with reinforced fidelity and naturalness. While deepfake detection technologies have manifested the ability to identify AI-generated content, their efficacy decreases as generative models become increasingly sophisticated. Furthermore, current research in the field has not adequately addressed the necessity for robust watermarking to safeguard the intellectual property rights associated with synthetic speech and generative models. To remedy this deficiency, we propose a \textbf{ro}bust generative \textbf{s}peech wat\textbf{e}rmarking method (TriniMark) for authenticating the generated content and safeguarding the copyrights by enabling the traceability of the diffusion model. We first design a structure-lightweight watermark encoder that embeds watermarks into the time-domain features of speech and reconstructs the waveform directly. A temporal-aware gated convolutional network is meticulously designed in the watermark decoder for bit-wise watermark recovery. Subsequently, the waveform-guided fine-tuning strategy is proposed for fine-tuning the diffusion model, which leverages the transferability of watermarks and enables the diffusion model to incorporate watermark knowledge effectively. When an attacker trains a surrogate model using the outputs of the target model, the embedded watermark can still be learned by the surrogate model and correctly extracted. Comparative experiments with state-of-the-art methods demonstrate the superior robustness of our method, particularly in countering compound attacks.
Similar Papers
Protecting Your Voice: Temporal-aware Robust Watermarking
Cryptography and Security
Makes fake voices sound real, but still detectable.
Visual Watermarking in the Era of Diffusion Models: Advances and Challenges
CV and Pattern Recognition
Protects pictures from being copied without permission.
Watermarking Discrete Diffusion Language Models
Cryptography and Security
Marks AI writing so you know it's fake.