Assessing the Effectiveness of Membership Inference on Generative Music

• URL: http://arxiv.org/abs/2512.21762v1
• Date: Thu, 25 Dec 2025 18:54:16 GMT
• Title: Assessing the Effectiveness of Membership Inference on Generative Music
• Authors: Kurtis Chow, Omar Samiullah, Vinesh Sridhar, Hewen Zhang,
• Abstract summary: We study the effect of several existing attacks on MuseGAN, a popular and influential generative music model.<n>Similar to prior work on generative audio MIAs, our findings suggest that music data is fairly resilient to known membership inference techniques.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative AI systems are quickly improving, now able to produce believable output in several modalities including images, text, and audio. However, this fast development has prompted increased scrutiny concerning user privacy and the use of copyrighted works in training. A recent attack on machine-learning models called membership inference lies at the crossroads of these two concerns. The attack is given as input a set of records and a trained model and seeks to identify which of those records may have been used to train the model. On one hand, this attack can be used to identify user data used to train a model, which may violate their privacy especially in sensitive applications such as models trained on medical data. On the other hand, this attack can be used by rights-holders as evidence that a company used their works without permission to train a model. Remarkably, it appears that no work has studied the effect of membership inference attacks (MIA) on generative music. Given that the music industry is worth billions of dollars and artists would stand to gain from being able to determine if their works were being used without permission, we believe this is a pressing issue to study. As such, in this work we begin a preliminary study into whether MIAs are effective on generative music. We study the effect of several existing attacks on MuseGAN, a popular and influential generative music model. Similar to prior work on generative audio MIAs, our findings suggest that music data is fairly resilient to known membership inference techniques.

Related papers

• Membership and Dataset Inference Attacks on Large Audio Generative Models [17.763094810756247]
  Generative audio models are often trained on vast corpora of artistic and commercial works.<n>A central question is whether one can reliably verify if an artist's material was included in training, thereby providing a means for copyright holders to protect their content.<n>In this work, we investigate the feasibility of such verification through membership inference attacks on open-source generative audio models.
  arXiv  Detail & Related papers  (2025-12-10T13:50:00Z)
• Music Boomerang: Reusing Diffusion Models for Data Augmentation and Audio Manipulation [49.062766449989525]
  Generative models of music audio are typically used to generate output based solely on a text prompt or melody.<n>Boomerang sampling, recently proposed for the image domain, allows generating output close to an existing example, using any pretrained diffusion model.
  arXiv  Detail & Related papers  (2025-07-07T10:46:07Z)
• Detecting Musical Deepfakes [0.0]
  This study investigates the detection of AI-generated songs using the FakeMusicCaps dataset.<n>To simulate real-world adversarial conditions, tempo stretching and pitch shifting were applied to the dataset.<n>Mel spectrograms were generated from the modified audio, then used to train and evaluate a convolutional neural network.
  arXiv  Detail & Related papers  (2025-05-03T21:45:13Z)
• Let Network Decide What to Learn: Symbolic Music Understanding Model Based on Large-scale Adversarial Pre-training [2.61072980439312]
  Mask Language Model (MLM) may introduce bias issues like racism discrimination in Natural Language Process (NLP)<n>We propose Adversarial-MidiBERT for SMU, which adaptively determines what to mask during via a masker network, rather than employing random masking.<n>We evaluate our method across four SMU tasks, and our approach demonstrates excellent performance in all cases.
  arXiv  Detail & Related papers  (2024-07-11T08:54:38Z)
• Music Era Recognition Using Supervised Contrastive Learning and Artist Information [11.126020721501956]
  Music era information can be an important feature for playlist generation and recommendation. An audio-based model is developed to predict the era from audio. For the case where the artist information is available, we extend the audio-based model to take multimodal inputs and develop a framework, called MultiModal Contrastive (MMC) learning, to enhance the training.
  arXiv  Detail & Related papers  (2024-07-07T13:43:55Z)
• MuPT: A Generative Symbolic Music Pretrained Transformer [56.09299510129221]
  We explore the application of Large Language Models (LLMs) to the pre-training of music. To address the challenges associated with misaligned measures from different tracks during generation, we propose a Synchronized Multi-Track ABC Notation (SMT-ABC Notation) Our contributions include a series of models capable of handling up to 8192 tokens, covering 90% of the symbolic music data in our training set.
  arXiv  Detail & Related papers  (2024-04-09T15:35:52Z)
• Noise Masking Attacks and Defenses for Pretrained Speech Models [22.220812007048423]
  Speech models are often trained on sensitive data in order to improve model performance, leading to potential privacy leakage. We consider noise masking attacks, introduced by Amid et al. 2022, which attack automatic speech recognition (ASR) models by requesting a transcript of an utterance which is partially replaced with noise. We extend these attacks beyond ASR models, to attack pretrained speech encoders.
  arXiv  Detail & Related papers  (2024-04-02T15:49:03Z)
• Exploring Musical Roots: Applying Audio Embeddings to Empower Influence Attribution for a Generative Music Model [6.476298483207895]
  We develop a methodology to identify similar pieces of music audio in a manner that is useful for understanding training data attribution. We compare the effect of applying CLMR and CLAP embeddings to similarity measurement in a set of 5 million audio clips used to train VampNet. This work is to incorporate automated influence attribution into generative modeling, which promises to let model creators and users move from ignorant appropriation to informed creation.
  arXiv  Detail & Related papers  (2024-01-25T22:20:42Z)
• MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training [74.32603591331718]
  We propose an acoustic Music undERstanding model with large-scale self-supervised Training (MERT), which incorporates teacher models to provide pseudo labels in the masked language modelling (MLM) style acoustic pre-training.<n> Experimental results indicate that our model can generalise and perform well on 14 music understanding tasks and attain state-of-the-art (SOTA) overall scores.
  arXiv  Detail & Related papers  (2023-05-31T18:27:43Z)
• Membership Inference Attacks against Synthetic Data through Overfitting Detection [84.02632160692995]
  We argue for a realistic MIA setting that assumes the attacker has some knowledge of the underlying data distribution. We propose DOMIAS, a density-based MIA model that aims to infer membership by targeting local overfitting of the generative model.
  arXiv  Detail & Related papers  (2023-02-24T11:27:39Z)
• MOVE: Effective and Harmless Ownership Verification via Embedded External Features [104.97541464349581]
  We propose an effective and harmless model ownership verification (MOVE) to defend against different types of model stealing simultaneously.<n>We conduct the ownership verification by verifying whether a suspicious model contains the knowledge of defender-specified external features.<n>We then train a meta-classifier to determine whether a model is stolen from the victim.
  arXiv  Detail & Related papers  (2022-08-04T02:22:29Z)
• Defending against Model Stealing via Verifying Embedded External Features [90.29429679125508]
  adversaries can steal' deployed models even when they have no training samples and can not get access to the model parameters or structures. We explore the defense from another angle by verifying whether a suspicious model contains the knowledge of defender-specified emphexternal features. Our method is effective in detecting different types of model stealing simultaneously, even if the stolen model is obtained via a multi-stage stealing process.
  arXiv  Detail & Related papers  (2021-12-07T03:51:54Z)
• Sampling Attacks: Amplification of Membership Inference Attacks by Repeated Queries [74.59376038272661]
  We introduce sampling attack, a novel membership inference technique that unlike other standard membership adversaries is able to work under severe restriction of no access to scores of the victim model. We show that a victim model that only publishes the labels is still susceptible to sampling attacks and the adversary can recover up to 100% of its performance. For defense, we choose differential privacy in the form of gradient perturbation during the training of the victim model as well as output perturbation at prediction time.
  arXiv  Detail & Related papers  (2020-09-01T12:54:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.