@inproceedings{senevirathna-sumanathilaka-2025-efficient,
title = "Efficient Financial Fraud Detection on Mobile Devices Using Lightweight Large Language Models",
author = "Senevirathna, Lakpriya and
Sumanathilaka, Deshan Koshala",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.126/",
pages = "1090--1098",
abstract = "The growth of mobile financial transactions presents new challenges for fraud detection, where traditional and ML methods often miss emerging patterns. While Large Language Models (LLMs) offer advanced language understanding, they are typically too resource-intensive for mobile deployment and raise privacy concerns due to cloud reliance. This paper proposes a lightweight, privacy-preserving approach by fine-tuning and quantizing compact LLMs for on-device fraud detection from textual data. Models were optimized using Open Neural Network Exchange (ONNX) conversion and quantization to ensure efficiency. The fine-tuned quantized Llama-160M-Chat-v1 (bnb4) achieved 99.47{\%} accuracy with a 168MB footprint, while fine-tuned quantized Qwen1.5-0.5B-Chat (bnb4) reached 99.50{\%} accuracy at 797MB. These results demonstrate that optimized LLMs can deliver accurate, real-time fraud detection on mobile devices without compromising user privacy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="senevirathna-sumanathilaka-2025-efficient">
<titleInfo>
<title>Efficient Financial Fraud Detection on Mobile Devices Using Lightweight Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lakpriya</namePart>
<namePart type="family">Senevirathna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deshan</namePart>
<namePart type="given">Koshala</namePart>
<namePart type="family">Sumanathilaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The growth of mobile financial transactions presents new challenges for fraud detection, where traditional and ML methods often miss emerging patterns. While Large Language Models (LLMs) offer advanced language understanding, they are typically too resource-intensive for mobile deployment and raise privacy concerns due to cloud reliance. This paper proposes a lightweight, privacy-preserving approach by fine-tuning and quantizing compact LLMs for on-device fraud detection from textual data. Models were optimized using Open Neural Network Exchange (ONNX) conversion and quantization to ensure efficiency. The fine-tuned quantized Llama-160M-Chat-v1 (bnb4) achieved 99.47% accuracy with a 168MB footprint, while fine-tuned quantized Qwen1.5-0.5B-Chat (bnb4) reached 99.50% accuracy at 797MB. These results demonstrate that optimized LLMs can deliver accurate, real-time fraud detection on mobile devices without compromising user privacy.</abstract>
<identifier type="citekey">senevirathna-sumanathilaka-2025-efficient</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.126/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>1090</start>
<end>1098</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Financial Fraud Detection on Mobile Devices Using Lightweight Large Language Models
%A Senevirathna, Lakpriya
%A Sumanathilaka, Deshan Koshala
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F senevirathna-sumanathilaka-2025-efficient
%X The growth of mobile financial transactions presents new challenges for fraud detection, where traditional and ML methods often miss emerging patterns. While Large Language Models (LLMs) offer advanced language understanding, they are typically too resource-intensive for mobile deployment and raise privacy concerns due to cloud reliance. This paper proposes a lightweight, privacy-preserving approach by fine-tuning and quantizing compact LLMs for on-device fraud detection from textual data. Models were optimized using Open Neural Network Exchange (ONNX) conversion and quantization to ensure efficiency. The fine-tuned quantized Llama-160M-Chat-v1 (bnb4) achieved 99.47% accuracy with a 168MB footprint, while fine-tuned quantized Qwen1.5-0.5B-Chat (bnb4) reached 99.50% accuracy at 797MB. These results demonstrate that optimized LLMs can deliver accurate, real-time fraud detection on mobile devices without compromising user privacy.
%U https://aclanthology.org/2025.ranlp-1.126/
%P 1090-1098
Markdown (Informal)
[Efficient Financial Fraud Detection on Mobile Devices Using Lightweight Large Language Models](https://aclanthology.org/2025.ranlp-1.126/) (Senevirathna & Sumanathilaka, RANLP 2025)
ACL