TS-RaMIA: Membership Inference Attacks for Symbolic Music Generation Models

Yuxuan Liu, rui sang, Peihong Zhang, Zhixin Li, Kunyang Zhang, Shengyuan He, Ye Li, Kaiyi Xu, Shengchen Li

Keywords: membership inference, generative music models, symbolic music, copyright auditing

TL;DR: TS-RaMIA is a structure-aware, forward-pass membership inference attack method for symbolic music that enables low-FPR copyright auditing across REMI and ABC models.

Abstract:

Artists and rights holders face growing concerns about unauthorized use of their copyrighted works in training generative models.
We introduce TS-RaMIA, a practical auditing framework enabling creators to test whether their symbolic music has been used without authorization. Unlike existing likelihood-based approaches that are confounded by piece length and density, TS-RaMIA exploits \emph{structural tokens}—bar lines, positions, and tempo markers encoding musical phrasing—through sample-level analysis and rigorous debiasing. Our method combines (i) length matching and conditional calibration to remove spurious confounders, (ii) tail-of-top-$k$ aggregation on structural tokens to amplify sparse memorization signals, and (iii) a lightweight meta-attacker fusing statistical cues via composer-stratified cross-validation. Evaluated on a 67M-parameter REMI Transformer trained on MAESTRO pieces, TS-RaMIA achieves AUC 0.826 and TPR@1%FPR 14.6%, while a debiased baseline drops to AUC 0.563. Cross-representation validation on NotaGen (ABC notation) yields comparable performance (AUC 0.73, TPR@1%FPR 8.9%), demonstrating transferability.
We release our code at https://anonymous.4open.science/r/TS-RaMIA-63F0.

Submission Number: 23