@inproceedings{janez-martino-etal-2024-comparative,
title = "Comparative Analysis of Natural Language Processing Models for Malware Spam Email Identification",
author = "J{\'a}{\~n}ez-Martino, Francisco and
Fidalgo, Eduardo and
Alaiz-Rodr{\'i}guez, Roc{\'i}o and
Carofilis, Andr{\'e}s and
Mart{\'i}nez-Mendoza, Alicia",
editor = "Mitkov, Ruslan and
Ezzini, Saad and
Ranasinghe, Tharindu and
Ezeani, Ignatius and
Khallaf, Nouran and
Acarturk, Cengiz and
Bradbury, Matthew and
El-Haj, Mo and
Rayson, Paul",
booktitle = "Proceedings of the First International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security",
month = jul,
year = "2024",
address = "Lancaster, UK",
publisher = "International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security",
url = "https://aclanthology.org/2024.nlpaics-1.7/",
pages = "59--63",
abstract = "Spam email is one of the main vectors of cyberattacks containing scams and spreading malware. Spam emails can contain malicious and external links and attachments with hidden malicious code. Hence, cybersecurity experts seek to detect this type of email to provide earlier and more detailed warnings for organizations and users. This work is based on a binary classification system (with and without malware) and evaluates models that have achieved high performance in other natural language applications, such as fastText, BERT, RoBERTa, DistilBERT, XLM-RoBERTa, and Large Language Models such as LLaMA and Mistral. Using the Spam Email Malware Detection (SEMD-600) dataset, we compare these models regarding precision, recall, F1 score, accuracy, and runtime. DistilBERT emerges as the most suitable option, achieving a recall of 0.792 and a runtime of 1.612 ms per email."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="janez-martino-etal-2024-comparative">
<titleInfo>
<title>Comparative Analysis of Natural Language Processing Models for Malware Spam Email Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="family">Jáñez-Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduardo</namePart>
<namePart type="family">Fidalgo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rocío</namePart>
<namePart type="family">Alaiz-Rodríguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrés</namePart>
<namePart type="family">Carofilis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Martínez-Mendoza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First 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">Saad</namePart>
<namePart type="family">Ezzini</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">Ignatius</namePart>
<namePart type="family">Ezeani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nouran</namePart>
<namePart type="family">Khallaf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cengiz</namePart>
<namePart type="family">Acarturk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Bradbury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mo</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security</publisher>
<place>
<placeTerm type="text">Lancaster, UK</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Spam email is one of the main vectors of cyberattacks containing scams and spreading malware. Spam emails can contain malicious and external links and attachments with hidden malicious code. Hence, cybersecurity experts seek to detect this type of email to provide earlier and more detailed warnings for organizations and users. This work is based on a binary classification system (with and without malware) and evaluates models that have achieved high performance in other natural language applications, such as fastText, BERT, RoBERTa, DistilBERT, XLM-RoBERTa, and Large Language Models such as LLaMA and Mistral. Using the Spam Email Malware Detection (SEMD-600) dataset, we compare these models regarding precision, recall, F1 score, accuracy, and runtime. DistilBERT emerges as the most suitable option, achieving a recall of 0.792 and a runtime of 1.612 ms per email.</abstract>
<identifier type="citekey">janez-martino-etal-2024-comparative</identifier>
<location>
<url>https://aclanthology.org/2024.nlpaics-1.7/</url>
</location>
<part>
<date>2024-07</date>
<extent unit="page">
<start>59</start>
<end>63</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparative Analysis of Natural Language Processing Models for Malware Spam Email Identification
%A Jáñez-Martino, Francisco
%A Fidalgo, Eduardo
%A Alaiz-Rodríguez, Rocío
%A Carofilis, Andrés
%A Martínez-Mendoza, Alicia
%Y Mitkov, Ruslan
%Y Ezzini, Saad
%Y Ranasinghe, Tharindu
%Y Ezeani, Ignatius
%Y Khallaf, Nouran
%Y Acarturk, Cengiz
%Y Bradbury, Matthew
%Y El-Haj, Mo
%Y Rayson, Paul
%S Proceedings of the First International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security
%D 2024
%8 July
%I International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security
%C Lancaster, UK
%F janez-martino-etal-2024-comparative
%X Spam email is one of the main vectors of cyberattacks containing scams and spreading malware. Spam emails can contain malicious and external links and attachments with hidden malicious code. Hence, cybersecurity experts seek to detect this type of email to provide earlier and more detailed warnings for organizations and users. This work is based on a binary classification system (with and without malware) and evaluates models that have achieved high performance in other natural language applications, such as fastText, BERT, RoBERTa, DistilBERT, XLM-RoBERTa, and Large Language Models such as LLaMA and Mistral. Using the Spam Email Malware Detection (SEMD-600) dataset, we compare these models regarding precision, recall, F1 score, accuracy, and runtime. DistilBERT emerges as the most suitable option, achieving a recall of 0.792 and a runtime of 1.612 ms per email.
%U https://aclanthology.org/2024.nlpaics-1.7/
%P 59-63
Markdown (Informal)
[Comparative Analysis of Natural Language Processing Models for Malware Spam Email Identification](https://aclanthology.org/2024.nlpaics-1.7/) (Jáñez-Martino et al., NLPAICS 2024)
ACL