Invisible Watermarking for Audio Generation Diffusion Models

September 22, 2023 ยท Declared Dead ยท ๐Ÿ› International Conference on Trust, Privacy and Security in Intelligent Systems and Applications

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Xirong Cao, Xiang Li, Divyesh Jadav, Yanzhao Wu, Zhehui Chen, Chen Zeng, Wenqi Wei arXiv ID 2309.13166 Category cs.SD: Sound Cross-listed cs.CR, cs.LG, eess.AS Citations 12 Venue International Conference on Trust, Privacy and Security in Intelligent Systems and Applications Last Checked 3 months ago
Abstract
Diffusion models have gained prominence in the image domain for their capabilities in data generation and transformation, achieving state-of-the-art performance in various tasks in both image and audio domains. In the rapidly evolving field of audio-based machine learning, safeguarding model integrity and establishing data copyright are of paramount importance. This paper presents the first watermarking technique applied to audio diffusion models trained on mel-spectrograms. This offers a novel approach to the aforementioned challenges. Our model excels not only in benign audio generation, but also incorporates an invisible watermarking trigger mechanism for model verification. This watermark trigger serves as a protective layer, enabling the identification of model ownership and ensuring its integrity. Through extensive experiments, we demonstrate that invisible watermark triggers can effectively protect against unauthorized modifications while maintaining high utility in benign audio generation tasks.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Sound

Died the same way โ€” ๐Ÿ‘ป Ghosted