Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Recolector de Cienci...arrow_drop_down
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
versions View all 2 versions
addClaim

Phishing detection using GNN

Authors: Serra Sors, Nil;

Phishing detection using GNN

Abstract

Els atacs de phishing representen una amenaça significativa tant per a individus com organitzacions, ja que sovint passen desapercebuts a causa de la seva habilitat per enganyar les víctimes. Tot i que s'han desenvolupat diverses tècniques per detectar aquests atacs, incloent mètodes d'aprenentatge automàtic, aquests solen limitar-se a analitzar el contingut del correu electrònic. En aquest treball explorem l'ús de la infraestructura i les relacions entre diferents atacs per a la detecció de phishing. Hem recopilat i processat metadades de tràfic de correus electrònics i les hem representat en forma de graf per a identificar patrons i tendències amb Xarxes Neuronals de Grafs. Els nostres experiments indiquen que, al considerar la infraestructura i les relacions dels correus electrònics, és possible millorar el rendiment de la detecció de phishing en comparació a limitar-se només al context del correu electrònic.

Phishing attacks present a significant threat to both individuals and organizations, as they can often go undetected due to their ability to deceive victims. While various techniques, including machine learning methods, have been developed for detecting these attacks, they are typically limited to analyzing the content of the email. In this thesis, we explore the use of infrastructure and relationships between different attacks in the detection of phishing. We collected and processed email traffic metadata and represented it in the form of a graph, in order to identify patterns and trends using Graph Neural Networks. Our experiments indicate that by considering infrastructure and relationships of the emails, it is possible to improve the performance of phishing detection compared to solely relying on the context of the email.

Country
Spain
Keywords

cybersecurity, Seguretat informàtica, ciberseguretat, Àrees temàtiques de la UPC::Informàtica::Seguretat informàtica, aprenentatge automàtic, Neural networks (Computer science), phishing detection, machine learning, Computer security, detecció de phishing, Machine learning, Aprenentatge automàtic, Xarxes neuronals (Informàtica), Graph Neural Networks, Xarxes neuronals per grafs

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    OpenAIRE UsageCounts
    Usage byUsageCounts
    visibility views 74
  • 74
    views
    Powered byOpenAIRE UsageCounts
Powered by OpenAIRE graph
Found an issue? Give us feedback
visibility
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
views
OpenAIRE UsageCountsViews provided by UsageCounts
0
Average
Average
Average
74
Related to Research communities
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!