arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.09654cs.LG
收藏

成员和数据集推断攻击在大型音频生成模型上

Membership and Dataset Inference Attacks on Large Audio Generative Models

Warsaw University of Technology(华沙技术大学);Sapienza University of Rome(罗马萨皮恩扎大学);IDEAS Research Institute(IDEAS研究所);NASK National Research Institute(NASK国家研究所)

Jakub Proboszcz, Paweł Kochanski, Karol Korszun, Donato Crisostomi, Giorgio Strano, Emanuele Rodolà, Kamil Deja, Jan Dubinski

AI总结:

本研究通过数据集推断攻击探讨了大型音频生成模型中验证艺术家作品是否被训练所用的可行性,发现DI在音频领域具有实际应用价值。

摘要:

生成音频模型基于扩散和自回归架构,已在质量和表达性上迅速进步。然而,这种进步却引发了紧迫的版权问题,因为此类模型通常是在大量艺术和商业作品的语料库上训练的。一个核心问题是是否可以可靠地验证某位艺术家的作品是否包含在训练中,从而为版权持有者保护其内容提供手段。在本工作中,我们通过成员推断攻击(MIA)研究了在开源生成音频模型上进行此类验证的可行性,这些攻击试图确定特定音频样本是否属于训练集。我们的实证结果表明,单独的成员推断在大规模情况下效果有限,因为对于训练在大规模和多样化数据集上的模型,每个样本的成员信号较弱。然而,艺术家和媒体所有者通常持有作品的集合,而不是孤立的样本。基于文本和视觉领域的先前工作,在本工作中我们专注于数据集推断(DI),它在多个样本上聚合多样化的成员证据。我们发现DI在音频领域是成功的,提供了一种更实际的机制来评估艺术家的作品是否对模型训练有所贡献。我们的结果表明DI是版权保护和大数据集问责在大型音频生成模型时代的一个有前途的方向。

英文摘要:

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 trained on vast corpora of artistic and commercial works. 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. In this work, we investigate the feasibility of such verification through membership inference attacks (MIA) on open-source generative audio models, which attempt to determine whether a specific audio sample was part of the training set. Our empirical results show that membership inference alone is of limited effectiveness at scale, as the per-sample membership signal is weak for models trained on large and diverse datasets. However, artists and media owners typically hold collections of works rather than isolated samples. Building on prior work in text and vision domains, in this work we focus on dataset inference (DI), which aggregates diverse membership evidence across multiple samples. We find that DI is successful in the audio domain, offering a more practical mechanism for assessing whether an artist's works contributed to model training. Our results suggest DI as a promising direction for copyright protection and dataset accountability in the era of large audio generative models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑