A multi-branched hybrid perceptron network for DDoS attack detection using dynamic feature adaptation and multi-instance learning

Basit Öğe Kaydı
dc.contributor.authorAl-Khayyat, Ali Tariq Kalil
dc.contributor.authorUçan, Osman Nuri
dc.date.accessioned2025-01-03T10:52:44Z
dc.date.available2025-01-03T10:52:44Z
dc.date.issued2024en_US
dc.departmentEnstitüler, Lisansüstü Eğitim Enstitüsü, Elektrik ve Bilgisayar Mühendisliği Ana Bilim Dalıen_US
dc.description.abstractThe increasing sophistication and frequency of Distributed Denial of Service (DDoS) attacks necessitate advanced detection systems. These attacks leave networks vulnerable to disruptions, resource overload, security breaches, and financial losses. Conventional detection systems suffer from high false positive rates, lower flexibility, and an inability to adapt dynamically to trending attack patterns. To address these limitations, our proposed work introduces a novel approach to tackling these challenges by merging a multi-branched hybrid perceptron network with dynamic feature adaptation and multi-instance learning. Our methodology features three key innovations: (1) Multi-Branched Hybrid Perceptron architecture, (2) Dynamic Feature Adaption, and (3) Dynamic Attention-Weighted Feature Fusion to improve feature representation and merging process. The proposed study was validated on three testing datasets: (1) UNSW-NB15, (2) CIC-IDS 2017, and (3) CIC-IDS 2018, and the results were compared with various state-of-the-approaches. The experimental results show that our model significantly outperforms existing methods. On UNSW-NB15, the model achieves an accuracy of 96.02% with a precision of 0.965, a recall of 0.963, and an F1-score of 0.9645. For CIC-IDS 2017, it reaches a near-perfect accuracy of 99.99% with all metrics at 1.00. On CIC-IDS 2018, the model performs with an accuracy of 99.96% and perfect precision, recall, and F1-scores of 1.00. Time complexity analysis shows that while the proposed intrusion detection framework takes 21.6 seconds on CIC-IDS 2017, 30.0 seconds on CSE-CIC-IDS2018, and 15.5 seconds on UNSW-NB15, it remains competitive with high performance. Despite its higher time complexity on UNSW-NB15, MHHPN provides superior detection capabilities, making it practical for real-time use in complicated and extensive networks.en_US
dc.identifier.citationAl-Khayyat, A. T. K., Uçan, O. N. (2024). A multi-branched hybrid perceptron network for DDoS attack detection using dynamic feature adaptation and multi-instance learning. IEEE Access. 10.1109/ACCESS.2024.3508028en_US
dc.identifier.issn2169-3536
dc.identifier.scopus2-s2.0-85212941919
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://hdl.handle.net/20.500.12939/5133
dc.identifier.wosWOS:001385614200038
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorAl-Khayyat, Ali Tariq Kalil
dc.institutionauthorUçan, Osman Nuri
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofIEEE Access
dc.relation.isversionof10.1109/ACCESS.2024.3508028en_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - İdari Personel ve Öğrencien_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectDDoS Attacksen_US
dc.subjectFalse Positivesen_US
dc.subjectHybrid Perceptron Networken_US
dc.subjectMulti-Instance Learningen_US
dc.subjectNetwork Traffic Analysisen_US
dc.titleA multi-branched hybrid perceptron network for DDoS attack detection using dynamic feature adaptation and multi-instance learning
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
A_Multi-Branched_Hybrid_Perceptron_Network_for_DDoS_Attack_Detection_Using_Dynamic_Feature_Adaptation_and_Multi-Instance_Learning.pdf
Boyut:
3.41 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
[ X ]
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu