Prediction and graph visualization of cyber attacks using graph attention networks

Basit Öğe Kaydı
dc.contributor.authorSoylu, Mucahit
dc.contributor.authorDas, Resul
dc.date.accessioned2026-04-04T13:35:09Z
dc.date.available2026-04-04T13:35:09Z
dc.date.issued2025
dc.departmentİnönü Üniversitesi
dc.description.abstractThis study proposes a hybrid approach for visualizing cyberattacks by combining the deep learning-based GAT model with JavaScript-based graph visualization tools. The model processes large, heterogeneous data from the UNSW-NB15 dataset to generate dynamic and meaningful graphs. In the data cleaning phase, missing and erroneous data were removed, unnecessary columns were discarded, and the data was transformed format suitable for modeling. Then, the data was converted into homogeneous graphs, and heterogeneous structures were created for analysis using the GAT model. GAT prioritizes relationships between nodes the graph with an attention mechanism, effectively detecting attack patterns. The analyzed data was then converted into interactive graphs using tools like SigmaJS, with attacks between the same nodes grouped reduce graph complexity. Users can explore these dynamic graphs in detail, examine attack types, and track events over time. This approach significantly benefits cybersecurity professionals, allowing them to better understand, track, and develop defense strategies against cyberattacks.
dc.identifier.doi10.1016/j.cose.2025.104534
dc.identifier.issn0167-4048
dc.identifier.issn1872-6208
dc.identifier.orcid0000-0002-4114-1390
dc.identifier.orcid0000-0002-6113-4649
dc.identifier.scopus2-s2.0-105006652500
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1016/j.cose.2025.104534
dc.identifier.urihttps://hdl.handle.net/11616/109661
dc.identifier.volume157
dc.identifier.wosWOS:001501145800001
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherElsevier Advanced Technology
dc.relation.ispartofComputers & Security
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_WOS_20250329
dc.subjectGraph visualization
dc.subjectCyber thread prediction
dc.subjectGraph attention networks
dc.subjectHeterogeneous graph
dc.titlePrediction and graph visualization of cyber attacks using graph attention networks
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu