SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2309.13166 · 2023

Invisible Watermarking for Audio Generation Diffusion Models

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2309.13166")
get_code_for_paper("2309.13166")
have("2309.13166")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2309.13166.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2309.13166.svg)](https://syntology.ai/paper/2309.13166)

Connect an agent — have() is free.