Newest papers

Membership Inference Attack on Private Evolution

Daniil Filienko, Sikha Pentyala, Martine De Cock · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.30514 · cited by 0 works (OpenAlex) · open-access PDF

Chinese

合成数据生成(SDG)是一个积极研究的方式,以便更广泛地实现私人数据的安全共享。私人进化(PE)等仅依据的SDG方法特别有吸引力,因为它们可以利用黑匣子访问预先训练的基础模型来生成高质量的数据,而无需对私人数据进行模型精确调节。PE明确设计用于在差异性隐私(DP)下生成合成数据。然而,正式的DP保证并不能消除对释放合成数据对敌对攻击的实际敏感性的经验性隐私审核的需求。在这项工作中,我们引入了第一个白盒子会员攻击(MIA)以投票为基础的算法,在PE框架下进行投票。通过利用它进行的过滤过程,将合成候选人对

Machine translation (Meta M2M100); the English original follows.

Abstract

Synthetic Data Generation (SDG) is an actively studied way to enable safe sharing of private data more broadly. Inference-only SDG methods, such as Private Evolution (PE), are particularly appealing, as they can leverage black-box access to pre-trained foundation models to generate high quality data without the need for model fine-tuning on the private data. PE is explicitly designed to produce synthetic data under Differential Privacy (DP). Yet formal DP guarantees do not eliminate the need for empirical privacy auditing of the practical susceptibility of released synthetic data to adversarial attacks. In this work, we introduce the first white-box Membership Inference Attack (MIA) tailored to the voting-based algorithm underlying the PE framework. By exploiting how the iterative filtering process biases the survival and proximity of synthetic candidates toward private instances, our attack achieves empirical performance indicating private data leakage in the PE applications across image, text, and tabular modalities.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Inference, Leverage (statistics), Differential privacy, Adversarial system, Synthetic data

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange