Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.09184 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914086004981760 |
|---|---|
| author | Charpentier, Lucas Georges Gabriel Lison, Pierre |
| author_facet | Charpentier, Lucas Georges Gabriel Lison, Pierre |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_09184 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Stronger Re-identification Attacks through Reasoning and Aggregation Charpentier, Lucas Georges Gabriel Lison, Pierre Computation and Language 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. |
| title | Stronger Re-identification Attacks through Reasoning and Aggregation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2510.09184 |