No Encore: Unlearning as Opt-Out in Music Generation

Jinju Kim, Taehan Kim, Abdul Waheed, Jong Hwan Ko, Rita Singh

Keywords: Text-to-Music, music, generative AI, music generation, copyright, safety, unlearning, generative unlearning, machine unlearning

TL;DR: We present a work-in-progress study investigating machine unlearning for text-to-music generation as a mechanism for opt-out, aimed at protecting against unauthorized exploitation in music AI.

Abstract: 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 application of unlearning for music generative AI models.

Track: Paper Track

Confirmation: Paper Track: I confirm that I have followed the formatting guideline and anonymized my submission.

Submission Number: 100