paper-with-me

Papers

Membership Inference Attacks against Large Audio Language Models

2026-03-30 · Jia-Kai Dong, Yu-Xiang Lin, Hung-Yi Lee arxiv

We present the first systematic Membership Inference Attack (MIA) evaluation of LALMs. Using Multi-modal Blind Baselines based on textual, spectral and prosodic features, we demonstrate that common audio datasets exhibit near-perfect train/test separability (AUC ~ 1.0) even without model inference, thus MIA may primarily detect distribution shift. We therefore introduce a blind-baseline protocol to control for this confound. Under this protocol, we identify that the distribution-matched datasets enable reliable MIA evaluation without distribution-shift artifacts. We benchmark multiple MIA methods and conduct modality disentanglement experiments on these datasets. The results reveal that LALM memorization is cross-modal, arising only from binding a speaker's vocal identity with its text. These findings establish a principled standard for auditing LALMs beyond spurious correlations. Our codebase is available at https://github.com/snooow1029/ALM_MIA.

📄 PDF Abstract BibTeX arXiv:2603.28378

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Membership and Dataset Inference Attacks on Large Audio Generative Models

2025-12-10 · Jakub Proboszcz, Paweł Kochanski, Karol Korszun, Donato Crisostomi 외 arxiv

Generative audio models, based on diffusion and autoregressive architectures, have advanced rapidly in both quality and expressiveness. This progress, however, raises pressing copyright concerns, as such models are often…

Membership Inference Attacks Against Self-supervised Speech Models

2021-11-09 · Wei-Cheng Tseng, Wei-Tsung Kao, Hung-Yi Lee

Recently, adapting the idea of self-supervised learning (SSL) on continuous speech has started gaining attention. SSL models pre-trained on a huge amount of unlabeled audio can generate general-purpose representations th…

Self-Supervised Learning

Reconstruction and Membership Inference Attacks against Generative Models

2019-06-07 · Benjamin Hilprecht, Martin Härterich, Daniel Bernau

We present two information leakage attacks that outperform previous work on membership inference against generative models. The first attack allows membership inference without assumptions on the type of the generative m…

Density EstimationInference AttackMembership Inference Attack

One Parameter Defense -- Defending against Data Inference Attacks via Differential Privacy

2022-03-13 · Dayong Ye, Sheng Shen, Tianqing Zhu, Bo Liu 외

Machine learning models are vulnerable to data inference attacks, such as membership inference and model inversion attacks. In these types of breaches, an adversary attempts to infer a data record's membership in a datas…

Label-Only Membership Inference Attacks

2020-07-28 · Christopher A. Choquette-Choo, Florian Tramer, Nicholas Carlini, Nicolas Papernot

Membership inference attacks are one of the simplest forms of privacy leakage for machine learning models: given a data point and model, determine whether the point was used to train the model. Existing membership infere…

L2 Regularization