Saved in:
Bibliographic Details
Main Authors: Kim, Jinju, Kim, Taehan, Waheed, Abdul, Hwan, Jong, Singh, Rita
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.06277
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918147010854912
author Kim, Jinju
Kim, Taehan
Waheed, Abdul
Hwan, Jong
Singh, Rita
author_facet Kim, Jinju
Kim, Taehan
Waheed, Abdul
Hwan, Jong
Singh, Rita
contents AI music generation is rapidly emerging in the creative industries, enabling intuitive music generation from textual descriptions. However, these systems pose risks in exploitation of copyrighted creations, raising ethical and legal concerns. In this paper, we present preliminary results on the first application of machine unlearning techniques from an ongoing research to prevent inadvertent usage of creative content. Particularly, we explore existing methods in machine unlearning to a pre-trained Text-to-Music (TTM) baseline and analyze their efficacy in unlearning pre-trained datasets without harming model performance. Through our experiments, we provide insights into the challenges of applying unlearning in music generation, offering a foundational analysis for future works on the application of unlearning for music generative models.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06277
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle No Encore: Unlearning as Opt-Out in Music Generation
Kim, Jinju
Kim, Taehan
Waheed, Abdul
Hwan, Jong
Singh, Rita
Computation and Language
AI music generation is rapidly emerging in the creative industries, enabling intuitive music generation from textual descriptions. However, these systems pose risks in exploitation of copyrighted creations, raising ethical and legal concerns. In this paper, we present preliminary results on the first application of machine unlearning techniques from an ongoing research to prevent inadvertent usage of creative content. Particularly, we explore existing methods in machine unlearning to a pre-trained Text-to-Music (TTM) baseline and analyze their efficacy in unlearning pre-trained datasets without harming model performance. Through our experiments, we provide insights into the challenges of applying unlearning in music generation, offering a foundational analysis for future works on the application of unlearning for music generative models.
title No Encore: Unlearning as Opt-Out in Music Generation
topic Computation and Language
url https://arxiv.org/abs/2509.06277