@inproceedings{yang-etal-2025-fraud,
title = "Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of {LLM} Against Augmented Fraud and Phishing Inducements",
author = "Yang, Shu and
Zhu, Shenzhe and
Wu, Zeyu and
Wang, Keyu and
Yao, Junchi and
Wu, Junchao and
Hu, Lijie and
Li, Mengdi and
Wong, Derek F. and
Wang, Di",
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.226/",
doi = "10.18653/v1/2025.findings-acl.226",
pages = "4374--4420",
ISBN = "979-8-89176-256-5",
abstract = "With the increasing integration of large language models (LLMs) into real-world applications such as finance, e-commerce, and recommendation systems, their susceptibility to misinformation and adversarial manipulation poses significant risks. Existing fraud detection benchmarks primarily focus on single-turn classification tasks, failing to capture the dynamic nature of real-world fraud attempts. To address this gap, we introduce Fraud-R1, a challenging bilingual benchmark designed to assess LLMs' ability to resist fraud and phishing attacks across five key fraud categories: Fraudulent Services, Impersonation, Phishing Scams, Fake Job Postings, and Online Relationships, covering subclasses. Our dataset comprises manually curated fraud cases from social media, news, phishing scam records, and prior fraud datasets."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2025-fraud">
<titleInfo>
<title>Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shu</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shenzhe</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeyu</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junchi</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junchao</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lijie</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengdi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Wang</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>With the increasing integration of large language models (LLMs) into real-world applications such as finance, e-commerce, and recommendation systems, their susceptibility to misinformation and adversarial manipulation poses significant risks. Existing fraud detection benchmarks primarily focus on single-turn classification tasks, failing to capture the dynamic nature of real-world fraud attempts. To address this gap, we introduce Fraud-R1, a challenging bilingual benchmark designed to assess LLMs’ ability to resist fraud and phishing attacks across five key fraud categories: Fraudulent Services, Impersonation, Phishing Scams, Fake Job Postings, and Online Relationships, covering subclasses. Our dataset comprises manually curated fraud cases from social media, news, phishing scam records, and prior fraud datasets.</abstract>
<identifier type="citekey">yang-etal-2025-fraud</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.226</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.226/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>4374</start>
<end>4420</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements
%A Yang, Shu
%A Zhu, Shenzhe
%A Wu, Zeyu
%A Wang, Keyu
%A Yao, Junchi
%A Wu, Junchao
%A Hu, Lijie
%A Li, Mengdi
%A Wong, Derek F.
%A Wang, Di
%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 yang-etal-2025-fraud
%X With the increasing integration of large language models (LLMs) into real-world applications such as finance, e-commerce, and recommendation systems, their susceptibility to misinformation and adversarial manipulation poses significant risks. Existing fraud detection benchmarks primarily focus on single-turn classification tasks, failing to capture the dynamic nature of real-world fraud attempts. To address this gap, we introduce Fraud-R1, a challenging bilingual benchmark designed to assess LLMs’ ability to resist fraud and phishing attacks across five key fraud categories: Fraudulent Services, Impersonation, Phishing Scams, Fake Job Postings, and Online Relationships, covering subclasses. Our dataset comprises manually curated fraud cases from social media, news, phishing scam records, and prior fraud datasets.
%R 10.18653/v1/2025.findings-acl.226
%U https://aclanthology.org/2025.findings-acl.226/
%U https://doi.org/10.18653/v1/2025.findings-acl.226
%P 4374-4420
Markdown (Informal)
[Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements](https://aclanthology.org/2025.findings-acl.226/) (Yang et al., Findings 2025)
ACL
- Shu Yang, Shenzhe Zhu, Zeyu Wu, Keyu Wang, Junchi Yao, Junchao Wu, Lijie Hu, Mengdi Li, Derek F. Wong, and Di Wang. 2025. Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements. In Findings of the Association for Computational Linguistics: ACL 2025, pages 4374–4420, Vienna, Austria. Association for Computational Linguistics.