Abstract
Text de-identification techniques are often used to mask personally identifiable information (PII) from documents. Their ability to conceal the identity of the individuals mentioned in a text is, however, hard to measure. Recent work has shown how the robustness of de-identification methods could be assessed by attempting the reverse process of _re-identification_, based on an automated adversary using its background knowledge to uncover the PIIs that have been masked. This paper presents two complementary strategies to build stronger re-identification attacks. We first show that (1) the _order_ in which the PII spans are re-identified matters, and that aggregating predictions across multiple orderings leads to improved results. We also find that (2) reasoning models can boost the re-identification performance, especially when the adversary is assumed to have access to extensive background knowledge.
Abstract (translated)
文本去识别技术通常用于从文档中屏蔽个人身份信息（PII）。然而，衡量这些技术隐藏文本中提及的个体身份的能力是困难的。最近的研究表明，可以通过尝试逆向过程——即“再识别”来评估去识别方法的稳健性。这种再识别基于自动化对手使用其背景知识来揭示已被屏蔽的PII。本文提出了两种互补策略以构建更强的再识别攻击。首先，我们展示了（1）在重新识别PII跨度时顺序的重要性，并且跨多个顺序聚合预测可以提高结果。此外，我们还发现（2）推理模型能够提升再识别性能，尤其是在假设对手具有大量背景知识的情况下更是如此。
URL
https://arxiv.org/abs/2510.09184
