Membership Inference Attack Against Music Diffusion Models via Generative Manifold Perturbation

Yuxuan Liu

ICASSP 2026oral0 citations

Membership Inference Attack Against Music Diffusion Models via Generative Manifold Perturbation

Abstract

Membership inference attacks (MIAs) test whether a specific audio clip was used to train a model, making them a key tool for auditing generative music models for copyright compliance. However, loss-based signals (e.g., reconstruction error) are weakly aligned with human perception in practice, yielding poor separability at the low false-positive rates (FPRs) required for forensics. We propose the Latent Stability Adversarial Probe (LSA-Probe), a white-box method that measures a geometric property of the reverse diffusion: the minimal time-normalized perturbation budget needed to cross a fixed perceptual degradation threshold at an intermediate diffusion state. We show that training members, residing in more stable regions, exhibit a significantly higher degradation cost.

BibTeX

@inproceedings{icassp2026_membershipinfere,
  title = {Membership Inference Attack Against Music Diffusion Models via Generative Manifold Perturbation},
  author = {Yuxuan Liu},
  booktitle = {ICASSP 2026},
  year = {2026}
}