Membership Inference Attack (MIA) identifies whether a record exists in a machine learning model's training set by querying the model. MIAs on the classic classification models have been well-studied, and recent works have started to explore how to transplant MIA onto generative models. Our investigation indicates that existing MIAs designed for generative models mainly depend on the overfitting in target models. However, overfitting can be avoided by employing various regularization techniques, whereas existing MIAs demonstrate poor performance in practice. Unlike overfitting, memorization is essential for deep learning models to attain optimal performance, making it a more prevalent phenomenon. Memorization in generative models leads to an increasing trend in the probability distribution of generating records around the member record. Therefore, we propose a Probabilistic Fluctuation Assessing Membership Inference Attack (PFAMI), a black-box MIA that infers memberships by detecting these trends via analyzing the overall probabilistic fluctuations around given records. We conduct extensive experiments across multiple generative models and datasets, which demonstrate PFAMI can improve the attack success rate (ASR) by about 27.9% when compared with the best baseline.

翻译：成员推断攻击（MIA）通过查询模型判断某个记录是否存在于机器学习模型的训练集中。针对经典分类模型的MIA已得到充分研究，近年来研究者开始探索如何将MIA迁移至生成模型。我们的研究表明，现有面向生成模型的MIA主要依赖于目标模型的过拟合现象。然而，采用各类正则化技术可有效避免过拟合，导致现有MIA的实际性能表现不佳。与过拟合不同，记忆效应对深度学习模型实现最优性能至关重要，因而是一种更为普遍的现象。生成模型中的记忆效应会导致成员记录周围的生成记录概率分布呈递增趋势。据此，我们提出了一种基于概率波动评估的成员推断攻击（PFAMI），这是一种黑盒MIA方法，通过分析给定记录周围的整体概率波动来检测上述趋势，从而推断成员关系。我们在多个生成模型和数据集上进行了大量实验，结果表明，与最优基线方法相比，PFAMI可将攻击成功率（ASR）提升约27.9%。