@inproceedings{savkin-etal-2025-spy,
title = "{SPY}: Enhancing Privacy with Synthetic {PII} Detection Dataset",
author = "Savkin, Maksim and
Ionov, Timur and
Konovalov, Vasily",
editor = "Ebrahimi, Abteen and
Haider, Samar and
Liu, Emmy and
Haider, Sammar and
Leonor Pacheco, Maria and
Wein, Shira",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = apr,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-srw.23/",
doi = "10.18653/v1/2025.naacl-srw.23",
pages = "236--246",
ISBN = "979-8-89176-192-6",
abstract = "We introduce **SPY Dataset**: a novel synthetic dataset for the task of **Personal Identifiable Information (PII) detection**, underscoring the significance of protecting PII in modern data processing. Our research innovates by leveraging Large Language Models (LLMs) to generate a dataset that emulates real-world PII scenarios. Through evaluation, we validate the dataset{'}s quality, providing a benchmark for PII detection. Comparative analyses reveal that while PII and Named Entity Recognition (NER) share similarities, **dedicated NER models exhibit limitations** when applied to PII-specific contexts. This work contributes to the field by making the generation methodology and the generated dataset publicly, thereby enabling further research and development in this field."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="savkin-etal-2025-spy">
<titleInfo>
<title>SPY: Enhancing Privacy with Synthetic PII Detection Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maksim</namePart>
<namePart type="family">Savkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timur</namePart>
<namePart type="family">Ionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasily</namePart>
<namePart type="family">Konovalov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abteen</namePart>
<namePart type="family">Ebrahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmy</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sammar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Leonor Pacheco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shira</namePart>
<namePart type="family">Wein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-192-6</identifier>
</relatedItem>
<abstract>We introduce **SPY Dataset**: a novel synthetic dataset for the task of **Personal Identifiable Information (PII) detection**, underscoring the significance of protecting PII in modern data processing. Our research innovates by leveraging Large Language Models (LLMs) to generate a dataset that emulates real-world PII scenarios. Through evaluation, we validate the dataset’s quality, providing a benchmark for PII detection. Comparative analyses reveal that while PII and Named Entity Recognition (NER) share similarities, **dedicated NER models exhibit limitations** when applied to PII-specific contexts. This work contributes to the field by making the generation methodology and the generated dataset publicly, thereby enabling further research and development in this field.</abstract>
<identifier type="citekey">savkin-etal-2025-spy</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-srw.23</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-srw.23/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>236</start>
<end>246</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SPY: Enhancing Privacy with Synthetic PII Detection Dataset
%A Savkin, Maksim
%A Ionov, Timur
%A Konovalov, Vasily
%Y Ebrahimi, Abteen
%Y Haider, Samar
%Y Liu, Emmy
%Y Haider, Sammar
%Y Leonor Pacheco, Maria
%Y Wein, Shira
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-192-6
%F savkin-etal-2025-spy
%X We introduce **SPY Dataset**: a novel synthetic dataset for the task of **Personal Identifiable Information (PII) detection**, underscoring the significance of protecting PII in modern data processing. Our research innovates by leveraging Large Language Models (LLMs) to generate a dataset that emulates real-world PII scenarios. Through evaluation, we validate the dataset’s quality, providing a benchmark for PII detection. Comparative analyses reveal that while PII and Named Entity Recognition (NER) share similarities, **dedicated NER models exhibit limitations** when applied to PII-specific contexts. This work contributes to the field by making the generation methodology and the generated dataset publicly, thereby enabling further research and development in this field.
%R 10.18653/v1/2025.naacl-srw.23
%U https://aclanthology.org/2025.naacl-srw.23/
%U https://doi.org/10.18653/v1/2025.naacl-srw.23
%P 236-246
Markdown (Informal)
[SPY: Enhancing Privacy with Synthetic PII Detection Dataset](https://aclanthology.org/2025.naacl-srw.23/) (Savkin et al., NAACL 2025)
ACL
- Maksim Savkin, Timur Ionov, and Vasily Konovalov. 2025. SPY: Enhancing Privacy with Synthetic PII Detection Dataset. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 236–246, Albuquerque, USA. Association for Computational Linguistics.