Saved in:
Bibliographic Details
Main Authors: Epple, Pascal, Shilov, Igor, Stevanoski, Bozhidar, de Montjoye, Yves-Alexandre
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.08549
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916519719469056
author Epple, Pascal
Shilov, Igor
Stevanoski, Bozhidar
de Montjoye, Yves-Alexandre
author_facet Epple, Pascal
Shilov, Igor
Stevanoski, Bozhidar
de Montjoye, Yves-Alexandre
contents Generative Artificial Intelligence (Gen-AI) models are increasingly used to produce content across domains, including text, images, and audio. While these models represent a major technical breakthrough, they gain their generative capabilities from being trained on enormous amounts of human-generated content, which often includes copyrighted material. In this work, we investigate whether audio watermarking techniques can be used to detect an unauthorized usage of content to train a music generation model. We compare outputs generated by a model trained on watermarked data to a model trained on non-watermarked data. We study factors that impact the model's generation behaviour: the watermarking technique, the proportion of watermarked samples in the training set, and the robustness of the watermarking technique against the model's tokenizer. Our results show that audio watermarking techniques, including some that are imperceptible to humans, can lead to noticeable shifts in the model's outputs. We also study the robustness of a state-of-the-art watermarking technique to removal techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08549
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Watermarking Training Data of Music Generation Models
Epple, Pascal
Shilov, Igor
Stevanoski, Bozhidar
de Montjoye, Yves-Alexandre
Machine Learning
Sound
Audio and Speech Processing
Generative Artificial Intelligence (Gen-AI) models are increasingly used to produce content across domains, including text, images, and audio. While these models represent a major technical breakthrough, they gain their generative capabilities from being trained on enormous amounts of human-generated content, which often includes copyrighted material. In this work, we investigate whether audio watermarking techniques can be used to detect an unauthorized usage of content to train a music generation model. We compare outputs generated by a model trained on watermarked data to a model trained on non-watermarked data. We study factors that impact the model's generation behaviour: the watermarking technique, the proportion of watermarked samples in the training set, and the robustness of the watermarking technique against the model's tokenizer. Our results show that audio watermarking techniques, including some that are imperceptible to humans, can lead to noticeable shifts in the model's outputs. We also study the robustness of a state-of-the-art watermarking technique to removal techniques.
title Watermarking Training Data of Music Generation Models
topic Machine Learning
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2412.08549