@inproceedings{vu-etal-2026-motigan,
title = "{M}oti{GAN}: Game Theory Meets the Motivated Intruder Test for Re-identification Risk Generation and Annotation in Pseudonymisation",
author = "Vu, Xuan-Son and
Dang, Tien Dat and
Volodina, Elena",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.256/",
pages = "4328--4337",
ISBN = "979-8-89176-460-6",
abstract = "Re-identification methods serve as a concrete instantiation of the Motivated Intruder Test in privacy-preserving problems, and current state-of-the-art attack techniques are predominantly built upon Large Language Models (LLMs) which are also core components of robust pseudonymized methods. Therefore, it requires the rich training dataset. However, as research demands continue to grow while publicly available data for each domain remains limited and the cost of direct human supervision is high, a central question arises: how can a human-in-the-loop approach be integrated to generate high-quality data and improve the performance of LLMs in psedonymization. To address this limitation, we propose MOTIGAN1 - a gamified framework that transforms the motivated intruder test into a competitive three population tournament. In this game, human characters and AI characters compete to re-identify individuals from each essay. At every stage, players both commit their guesses and contribute to enriching the synthesized dataset. In our experiments, the synthesized dataset contributes to improving the performance of multiple models in several experiments (achieving up to 37.6{\%} improvement on a well-established benchmark)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vu-etal-2026-motigan">
<titleInfo>
<title>MotiGAN: Game Theory Meets the Motivated Intruder Test for Re-identification Risk Generation and Annotation in Pseudonymisation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuan-Son</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tien</namePart>
<namePart type="given">Dat</namePart>
<namePart type="family">Dang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Volodina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>Re-identification methods serve as a concrete instantiation of the Motivated Intruder Test in privacy-preserving problems, and current state-of-the-art attack techniques are predominantly built upon Large Language Models (LLMs) which are also core components of robust pseudonymized methods. Therefore, it requires the rich training dataset. However, as research demands continue to grow while publicly available data for each domain remains limited and the cost of direct human supervision is high, a central question arises: how can a human-in-the-loop approach be integrated to generate high-quality data and improve the performance of LLMs in psedonymization. To address this limitation, we propose MOTIGAN1 - a gamified framework that transforms the motivated intruder test into a competitive three population tournament. In this game, human characters and AI characters compete to re-identify individuals from each essay. At every stage, players both commit their guesses and contribute to enriching the synthesized dataset. In our experiments, the synthesized dataset contributes to improving the performance of multiple models in several experiments (achieving up to 37.6% improvement on a well-established benchmark).</abstract>
<identifier type="citekey">vu-etal-2026-motigan</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.256/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>4328</start>
<end>4337</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MotiGAN: Game Theory Meets the Motivated Intruder Test for Re-identification Risk Generation and Annotation in Pseudonymisation
%A Vu, Xuan-Son
%A Dang, Tien Dat
%A Volodina, Elena
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F vu-etal-2026-motigan
%X Re-identification methods serve as a concrete instantiation of the Motivated Intruder Test in privacy-preserving problems, and current state-of-the-art attack techniques are predominantly built upon Large Language Models (LLMs) which are also core components of robust pseudonymized methods. Therefore, it requires the rich training dataset. However, as research demands continue to grow while publicly available data for each domain remains limited and the cost of direct human supervision is high, a central question arises: how can a human-in-the-loop approach be integrated to generate high-quality data and improve the performance of LLMs in psedonymization. To address this limitation, we propose MOTIGAN1 - a gamified framework that transforms the motivated intruder test into a competitive three population tournament. In this game, human characters and AI characters compete to re-identify individuals from each essay. At every stage, players both commit their guesses and contribute to enriching the synthesized dataset. In our experiments, the synthesized dataset contributes to improving the performance of multiple models in several experiments (achieving up to 37.6% improvement on a well-established benchmark).
%U https://aclanthology.org/2026.emnlp-industry.256/
%P 4328-4337
Markdown (Informal)
[MotiGAN: Game Theory Meets the Motivated Intruder Test for Re-identification Risk Generation and Annotation in Pseudonymisation](https://aclanthology.org/2026.emnlp-industry.256/) (Vu et al., EMNLP 2026)
ACL