@inproceedings{martinez-murillo-etal-2026-exploring,
title = "Exploring Cross-Lingual Transfer in Transformer-Based Fraud Detection Models",
author = "Martinez-Murillo, Ivan and
Sep{\'u}lveda-Torres, Robiert and
Consuegra-Ayala, Juan Pablo",
editor = "Mitkov, Ruslan and
Mu{\~n}oz, Rafael and
Lloret, Elena and
Ranasinghe, Tharindu and
Estevanell-Valladares, Ernesto L. and
Lamsiyah, Salima and
Montoyo, Andr{\'e}s and
Ezzini, Saad",
booktitle = "Proceedings of the Second International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security",
month = jun,
year = "2026",
address = "Alicante, Spain",
publisher = "Department of Languages and Information Systems, University of Alicante",
url = "https://aclanthology.org/2026.nlpaics-1.1/",
pages = "1--10",
abstract = "Digital communication channels have become major vectors for large-scale cyber fraud, including spam, phishing, and recruitment scams, causing significant financial losses and eroding user trust. While transformer-based models have improved text classification, most systems remain English-centric, limiting their effectiveness in multilingual environments and across diverse fraud typologies. In this work, we hypothesize that fraud detection models trained in a single language can exhibit cross-lingual generalization capabilities. We investigate the use of Natural Language Processing (NLP) for detecting multiple forms of textual fraud by developing and evaluating three transformer-based discriminative models targeting spam, phishing, and fake job postings. Specifically, we compare two architectures{---}MrBERT (308M parameters) and mROBERTa (283M parameters){---}across English, Spanish, and Valencian data. Our results demonstrate that while models trained exclusively on English achieve near-perfect performance in-language (F1 {\ensuremath{\approx}} 0.98), they exhibit limited cross-lingual generalization in other languages such as Spanish (F1 {\ensuremath{\approx}} 0.44 for phishing detection, and F1 {\ensuremath{\approx}} 0.85 for spam detection). However, incorporating multilingual training data dramatically improves performance in target languages (F1 {\ensuremath{\approx}} 0.95{--}0.99) while maintaining or even enhancing English accuracy. We further observe that cross-lingual transfer is most effective when datasets are parallel or closely aligned. These findings underscore the critical importance of multilingual data inclusion for building robust, scalable cybersecurity frameworks in diverse linguistic settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="martinez-murillo-etal-2026-exploring">
<titleInfo>
<title>Exploring Cross-Lingual Transfer in Transformer-Based Fraud Detection Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Martinez-Murillo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robiert</namePart>
<namePart type="family">Sepúlveda-Torres</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Pablo</namePart>
<namePart type="family">Consuegra-Ayala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Muñoz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Lloret</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ernesto</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Estevanell-Valladares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salima</namePart>
<namePart type="family">Lamsiyah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrés</namePart>
<namePart type="family">Montoyo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saad</namePart>
<namePart type="family">Ezzini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Department of Languages and Information Systems, University of Alicante</publisher>
<place>
<placeTerm type="text">Alicante, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Digital communication channels have become major vectors for large-scale cyber fraud, including spam, phishing, and recruitment scams, causing significant financial losses and eroding user trust. While transformer-based models have improved text classification, most systems remain English-centric, limiting their effectiveness in multilingual environments and across diverse fraud typologies. In this work, we hypothesize that fraud detection models trained in a single language can exhibit cross-lingual generalization capabilities. We investigate the use of Natural Language Processing (NLP) for detecting multiple forms of textual fraud by developing and evaluating three transformer-based discriminative models targeting spam, phishing, and fake job postings. Specifically, we compare two architectures—MrBERT (308M parameters) and mROBERTa (283M parameters)—across English, Spanish, and Valencian data. Our results demonstrate that while models trained exclusively on English achieve near-perfect performance in-language (F1 \ensuremath\approx 0.98), they exhibit limited cross-lingual generalization in other languages such as Spanish (F1 \ensuremath\approx 0.44 for phishing detection, and F1 \ensuremath\approx 0.85 for spam detection). However, incorporating multilingual training data dramatically improves performance in target languages (F1 \ensuremath\approx 0.95–0.99) while maintaining or even enhancing English accuracy. We further observe that cross-lingual transfer is most effective when datasets are parallel or closely aligned. These findings underscore the critical importance of multilingual data inclusion for building robust, scalable cybersecurity frameworks in diverse linguistic settings.</abstract>
<identifier type="citekey">martinez-murillo-etal-2026-exploring</identifier>
<location>
<url>https://aclanthology.org/2026.nlpaics-1.1/</url>
</location>
<part>
<date>2026-06</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Cross-Lingual Transfer in Transformer-Based Fraud Detection Models
%A Martinez-Murillo, Ivan
%A Sepúlveda-Torres, Robiert
%A Consuegra-Ayala, Juan Pablo
%Y Mitkov, Ruslan
%Y Muñoz, Rafael
%Y Lloret, Elena
%Y Ranasinghe, Tharindu
%Y Estevanell-Valladares, Ernesto L.
%Y Lamsiyah, Salima
%Y Montoyo, Andrés
%Y Ezzini, Saad
%S Proceedings of the Second International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security
%D 2026
%8 June
%I Department of Languages and Information Systems, University of Alicante
%C Alicante, Spain
%F martinez-murillo-etal-2026-exploring
%X Digital communication channels have become major vectors for large-scale cyber fraud, including spam, phishing, and recruitment scams, causing significant financial losses and eroding user trust. While transformer-based models have improved text classification, most systems remain English-centric, limiting their effectiveness in multilingual environments and across diverse fraud typologies. In this work, we hypothesize that fraud detection models trained in a single language can exhibit cross-lingual generalization capabilities. We investigate the use of Natural Language Processing (NLP) for detecting multiple forms of textual fraud by developing and evaluating three transformer-based discriminative models targeting spam, phishing, and fake job postings. Specifically, we compare two architectures—MrBERT (308M parameters) and mROBERTa (283M parameters)—across English, Spanish, and Valencian data. Our results demonstrate that while models trained exclusively on English achieve near-perfect performance in-language (F1 \ensuremath\approx 0.98), they exhibit limited cross-lingual generalization in other languages such as Spanish (F1 \ensuremath\approx 0.44 for phishing detection, and F1 \ensuremath\approx 0.85 for spam detection). However, incorporating multilingual training data dramatically improves performance in target languages (F1 \ensuremath\approx 0.95–0.99) while maintaining or even enhancing English accuracy. We further observe that cross-lingual transfer is most effective when datasets are parallel or closely aligned. These findings underscore the critical importance of multilingual data inclusion for building robust, scalable cybersecurity frameworks in diverse linguistic settings.
%U https://aclanthology.org/2026.nlpaics-1.1/
%P 1-10
Markdown (Informal)
[Exploring Cross-Lingual Transfer in Transformer-Based Fraud Detection Models](https://aclanthology.org/2026.nlpaics-1.1/) (Martinez-Murillo et al., NLPAICS 2026)
ACL
- Ivan Martinez-Murillo, Robiert Sepúlveda-Torres, and Juan Pablo Consuegra-Ayala. 2026. Exploring Cross-Lingual Transfer in Transformer-Based Fraud Detection Models. In Proceedings of the Second International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security, pages 1–10, Alicante, Spain. Department of Languages and Information Systems, University of Alicante.