SoK：重新思考表格机器学习中的成员推断
SoK: Rethinking Membership Inference in Tabular Machine Learning
AI总结：
本文针对表格机器学习的成员推断攻击（MIAs）提出新分类法，研究发现高类别粒度、高多数类占比的数据集更易受攻击，现有防御无法充分保护含独特特征的敏感个体。
摘要：
成员推断攻击（MIAs）是当前评估机器学习应用隐私的主流方法。尽管其重要性突出，但仍有若干未探索的问题，尤其是针对表格数据的相关问题。现有评估主要聚焦于高维数据集，而中小规模数据集的隐私行为尚未得到研究。本文提出了一种新的MIAs分类法，并对影响脆弱性的因素展开了全面研究。我们在多种表格数据集和模型架构上评估了四种不同的最先进攻击方法。结果表明，类别粒度更高、多数类占比更大的数据集更易受MIAs影响。我们进一步证明，高级MIAs高度依赖目标模型的对抗性知识，而无参考模型的攻击常能取得统计上可比的结果。最重要的是，我们发现具有独特特征（单样本）的记录即使应用常见防御措施后仍高度脆弱。这些发现表明，当前防御措施降低了平均泄露程度，但未能充分保护最敏感的个体。
英文摘要：
Membership Inference Attacks (MIAs) are currently the dominant approach to evaluating privacy in machine learning applications. Despite their significance, several concerns remain unexplored, particularly with regard to tabular data. Existing evaluations focus predominantly on high-dimensional datasets, leaving the privacy behavior of small-to-medium datasets unexplored. In this paper, we present a new taxonomy for MIAs and conduct a comprehensive study of the factors influencing vulnerability. We evaluate four distinct state-of-the-art attacks across diverse tabular datasets and model architectures. Our results show that datasets with higher class granularity and majority class percentage are more susceptible to MIAs. We further demonstrate that advanced MIAs are highly dependent on adversarial knowledge of the target model, while reference model-free attacks often achieve statistically comparable results. Most importantly, we show that records with unique signatures (single-outs) remain highly vulnerable, even when common defenses are applied. These findings indicate that current defenses reduce average leakage, but fail to adequately protect the most sensitive individuals.
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。
