提出无需公开数据的私有表格上下文学习方法，有效防止隐私泄露。
TabPATE: Differentially Private Tabular In-Context Learning Without Public Data
- 将私有数据分片给多个教师模型，私有聚合生成合成查询
- 在多个基准上保持竞争力性能，成员推断攻击成功率接近随机
- 适用于无可用公共数据的隐私敏感表格学习场景
表格基础模型可从小规模标注数据中实现精准的上下文学习（ICL），但置于上下文中的私有记录可能通过模型预测泄露。我们首次证明，即使基础的成员推断攻击也对表格ICL有效，从而激发正式隐私保护需求。为此，我们提出TabPATE——一种无需依赖公开分布数据的差分隐私PATE式防御方法。TabPATE将私有上下文分割至多个教师模型，对合成表格查询的标签进行私有聚合，并将生成的带标签查询作为学生模型的上下文。由于表格特征有界且维度较低，仅基于特征范围或轻度私化的边缘分布即可生成有效查询。在多个表格基准测试中，TabPATE在保持优异性能的同时，使成员推断攻击成功率降至近随机水平，为无公共数据场景下的私有表格上下文学习提供了实用路径。
原文摘要 · Abstract (English)
Tabular foundation models enable accurate in-context learning (ICL) from small labeled datasets, but the private records placed in context can leak through model predictions. We first show that even basic membership inference attacks succeed against tabular ICL, motivating formal privacy protection. We then introduce TabPATE, a differentially private PATE-style defense for tabular ICL that does not require public in-distribution data. TabPATE partitions the private context across teacher models, privately aggregates their labels on synthetic tabular queries, and releases the resulting labeled queries as a student context. Because tabular features are bounded and relatively low-dimensional, useful queries can be generated from feature ranges alone or from lightly privatized marginals. Across tabular benchmarks, TabPATE preserves competitive utility while reducing membership inference to near-random success, providing a practical path to private tabular ICL without public data.
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。