标题： 生成模型的黎曼几何指纹 显示英文标题

标题： Riemannian-Geometric Fingerprints of Generative Models

摘要： 最近生成模型（GMs）的突破性进展和快速整合引发了对模型归因及其指纹问题的兴趣。 例如，服务提供商需要可靠的方法来验证其模型以保护其知识产权，而用户和执法部门则希望验证生成内容的来源以确保责任和信任。 此外，随着越来越多的模型生成数据被反馈到常用于训练的数据源（如YouTube）中（“反刍训练”），模型崩溃的威胁正在增加，这加剧了区分合成数据与人类数据的必要性。 然而，我们相信，对生成模型指纹的理解仍存在差距，这源于缺乏一种可以系统地定义、表示和分析指纹的正式框架。 为了解决这一差距，我们采用了几何方法，利用黎曼几何提出了生成模型的人工制品和指纹的新定义，这使我们能够利用微分几何的丰富理论。 我们的新定义通过从数据中学习黎曼度量，并用测地线距离和基于kNN的黎曼质心代替欧几里得距离和最近邻搜索，将先前的工作（Song等人，2024年）推广到非欧几里得流形。 我们将该理论应用于一种新的基于梯度的算法，以在实践中计算指纹。 结果表明，该方法在区分大量生成模型方面更为有效，这些模型跨越了2种不同分辨率（64乘64，256乘256）的4个不同数据集，27种模型架构以及2种模态（视觉、视觉-语言）。 使用我们提出的定义显著提高了模型归因的性能，以及对未见过的数据集、模型类型和模态的泛化能力，表明其实际有效性。 显示英文摘要

摘要： Recent breakthroughs and rapid integration of generative models (GMs) have sparked interest in the problem of model attribution and their fingerprints. For instance, service providers need reliable methods of authenticating their models to protect their IP, while users and law enforcement seek to verify the source of generated content for accountability and trust. In addition, a growing threat of model collapse is arising, as more model-generated data are being fed back into sources (e.g., YouTube) that are often harvested for training ("regurgitative training"), heightening the need to differentiate synthetic from human data. Yet, a gap still exists in understanding generative models' fingerprints, we believe, stemming from the lack of a formal framework that can define, represent, and analyze the fingerprints in a principled way. To address this gap, we take a geometric approach and propose a new definition of artifact and fingerprint of GMs using Riemannian geometry, which allows us to leverage the rich theory of differential geometry. Our new definition generalizes previous work (Song et al., 2024) to non-Euclidean manifolds by learning Riemannian metrics from data and replacing the Euclidean distances and nearest-neighbor search with geodesic distances and kNN-based Riemannian center of mass. We apply our theory to a new gradient-based algorithm for computing the fingerprints in practice. Results show that it is more effective in distinguishing a large array of GMs, spanning across 4 different datasets in 2 different resolutions (64 by 64, 256 by 256), 27 model architectures, and 2 modalities (Vision, Vision-Language). Using our proposed definition significantly improves the performance on model attribution, as well as a generalization to unseen datasets, model types, and modalities, suggesting its practical efficacy.