arXiv cs.CL· Pierre Lison, Mark Anderson·· 13 小时前AI 评分31
用 LLM 重写抵御基于搜索的链接攻击：保护去标识化文档
Protecting De-identified Documents from Search-based Linkage Attacks
AI 导读
研究者提出一种两步方法抵御基于搜索的链接攻击：先为文本集合中的 N-gram 构建倒排索引，定位出现于少于 k 篇文档的 N-gram 及其组合，再用 LLM 重写器迭代改写这些片段直至无法链接。在法院案件和 Wikipedia 传记两个数据集上，该方法能有效阻止基于搜索的链接并保持内容忠实，但更先进的语义导向方法仍可实现链接。
正文 · 原文
Abstract:While de-identification models can help conceal the identity of the individuals mentioned in a document, they fail to address linkage risks, defined as the potential to map the de-identified text back to its source. One straightforward way to perform such linkages is to extract phrases from the de-identified document and check their presence in the original dataset. This paper presents a method to counter search-based linkage attacks while preserving the semantic integrity of the text. The method proceeds in two steps. We first construct an inverted index of the N-grams occurring in the text collection, making it possible to efficiently determine which N-grams appear in fewer than $k$ documents, either alone or in combination with other N-grams. An LLM-based rewriter is then iteratively queried to reformulate those spans until linkage is no longer possible. Experimental results on two datasets (court cases and Wikipedia biographies) show that the rewriting method can effectively prevent search-based linkages while remaining faithful to the original content. However, we also highlight that linkages remain feasible with the help of more advanced, semantics-oriented approaches.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2510.06383 [cs.CL] |
| (or arXiv:2510.06383v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2510.06383 arXiv-issued DOI via DataCite |
Submission history
From: Pierre Lison [view email]
[v1]
Tue, 7 Oct 2025 19:02:21 UTC (77 KB)
[v2]
Mon, 16 Mar 2026 20:06:11 UTC (152 KB)
[v3]
Wed, 21 Oct 2026 15:29:32 UTC (167 KB)
来源：arXiv cs.CL · arxiv.org