@inproceedings{saxena-etal-2025-matched,
title = "{MATCHED}: Multimodal Authorship-Attribution To Combat Human Trafficking in Escort-Advertisement Data",
author = "Saxena, Vageesh Kumar and
Ashpole, Benjamin and
Van Dijck, Gijs and
Spanakis, Gerasimos",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.225/",
doi = "10.18653/v1/2025.findings-acl.225",
pages = "4334--4373",
ISBN = "979-8-89176-256-5",
abstract = "Human trafficking (HT) remains a critical issue, with traffickers increasingly leveraging online escort advertisements to advertise victims anonymously. Existing detection methods, including text-based Authorship Attribution (AA), overlook the multimodal nature of these ads, which combine text and images. To bridge this gap, we introduce MATCHED, a multimodal AA dataset comprising 27,619 unique text descriptions and 55,115 unique images sourced from Backpage across seven U.S. cities in four geographic regions. This study extensively benchmarks text-only, vision-only, and multimodal baselines for vendor identification and verification tasks, employing multitask (joint) training objectives that achieve superior classification and retrieval performance on in-sample and out-of-data distribution datasets. The results demonstrate that while text remains the dominant modality, integrating visual features adds stylistic cues that enrich model performance. Moreover, text-image alignment strategies like CLIP and BLIP2 struggle due to low semantic overlap and vague connections between the modalities of escort ads, with end-to-end multimodal training proving more robust. Our findings emphasize the potential of multimodal AA to combat HT, providing Law Enforcement Agencies with robust tools to link advertisements and disrupt trafficking networks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saxena-etal-2025-matched">
<titleInfo>
<title>MATCHED: Multimodal Authorship-Attribution To Combat Human Trafficking in Escort-Advertisement Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vageesh</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Saxena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Ashpole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gijs</namePart>
<namePart type="family">Van Dijck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerasimos</namePart>
<namePart type="family">Spanakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Human trafficking (HT) remains a critical issue, with traffickers increasingly leveraging online escort advertisements to advertise victims anonymously. Existing detection methods, including text-based Authorship Attribution (AA), overlook the multimodal nature of these ads, which combine text and images. To bridge this gap, we introduce MATCHED, a multimodal AA dataset comprising 27,619 unique text descriptions and 55,115 unique images sourced from Backpage across seven U.S. cities in four geographic regions. This study extensively benchmarks text-only, vision-only, and multimodal baselines for vendor identification and verification tasks, employing multitask (joint) training objectives that achieve superior classification and retrieval performance on in-sample and out-of-data distribution datasets. The results demonstrate that while text remains the dominant modality, integrating visual features adds stylistic cues that enrich model performance. Moreover, text-image alignment strategies like CLIP and BLIP2 struggle due to low semantic overlap and vague connections between the modalities of escort ads, with end-to-end multimodal training proving more robust. Our findings emphasize the potential of multimodal AA to combat HT, providing Law Enforcement Agencies with robust tools to link advertisements and disrupt trafficking networks.</abstract>
<identifier type="citekey">saxena-etal-2025-matched</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.225</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.225/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>4334</start>
<end>4373</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MATCHED: Multimodal Authorship-Attribution To Combat Human Trafficking in Escort-Advertisement Data
%A Saxena, Vageesh Kumar
%A Ashpole, Benjamin
%A Van Dijck, Gijs
%A Spanakis, Gerasimos
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F saxena-etal-2025-matched
%X Human trafficking (HT) remains a critical issue, with traffickers increasingly leveraging online escort advertisements to advertise victims anonymously. Existing detection methods, including text-based Authorship Attribution (AA), overlook the multimodal nature of these ads, which combine text and images. To bridge this gap, we introduce MATCHED, a multimodal AA dataset comprising 27,619 unique text descriptions and 55,115 unique images sourced from Backpage across seven U.S. cities in four geographic regions. This study extensively benchmarks text-only, vision-only, and multimodal baselines for vendor identification and verification tasks, employing multitask (joint) training objectives that achieve superior classification and retrieval performance on in-sample and out-of-data distribution datasets. The results demonstrate that while text remains the dominant modality, integrating visual features adds stylistic cues that enrich model performance. Moreover, text-image alignment strategies like CLIP and BLIP2 struggle due to low semantic overlap and vague connections between the modalities of escort ads, with end-to-end multimodal training proving more robust. Our findings emphasize the potential of multimodal AA to combat HT, providing Law Enforcement Agencies with robust tools to link advertisements and disrupt trafficking networks.
%R 10.18653/v1/2025.findings-acl.225
%U https://aclanthology.org/2025.findings-acl.225/
%U https://doi.org/10.18653/v1/2025.findings-acl.225
%P 4334-4373
Markdown (Informal)
[MATCHED: Multimodal Authorship-Attribution To Combat Human Trafficking in Escort-Advertisement Data](https://aclanthology.org/2025.findings-acl.225/) (Saxena et al., Findings 2025)
ACL