提出关系感知的隐私攻击方法，提升对表格扩散模型的成员推理能力。
FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion Models
- 利用表间关联信息增强目标表特征，注入关系成员信号。
- 白盒下最高提升53%攻击准确率，黑盒下提升22%。
- 适合评估多表敏感数据中扩散模型的隐私风险。
扩散模型是表格数据合成的主流方法，被广泛用于共享敏感记录，其隐私保护能力成为关键问题。成员推理攻击是评估隐私风险的标准工具，但现有方法仅适用于单表场景，忽略真实数据中的多表关联结构。在实际攻击中，攻击者训练时可获取辅助表信息（如父表），但推理时仅能观测目标表的属性值。本文提出FERMI（FEature-mapping for Relational Membership Inference），通过将关系成员信号融入单表特征，填补该空白。在三种表格扩散架构和三个真实世界多表数据集上，FERMI显著优于单表基线：白盒设置下，TPR@$0.1$FPR最高提升53%；黑盒设置下提升22%。
原文摘要 · Abstract (English)
Diffusion models are the leading approach for tabular data synthesis and are increasingly used to share sensitive records. Whether they actually protect privacy has become a pressing question. Membership inference attacks are the standard tool for this purpose, yet existing attacks assume a single-table setting and ignore the multi-relational structure of real sensitive data. A core challenge in assessing privacy risks from membership inference attacks in multi-table settings is how to leverage auxiliary information from relations associated with the target table, such as its parent tables. Particularly, we study a practical setting in which such auxiliary information is available only when training the attack model. At inference time, the attacker observes only the attribute values of the target record from the target table. We propose FERMI (FEature-mapping for Relational Membership Inference), which resolves this gap by enriching single-table features with relational membership signal. Across three tabular diffusion architectures and three real-world relational datasets, FERMI consistently improves attack performance over single-table baselines, with TPR@$0.1$FPR rising by up to 53% over the single-table baseline in the white-box setting and 22% in the black-box setting.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。