Bahçeşehir Üniversitesi (Bahçeşehir University) - Dr. Ehsan Nowroozi (2024) Patent TR2023004922A1: Deep learning method to strengthen computer network security. .

	PDF (Patent Translated in English (Google)) 52568 NOWROOZI_ Patent_TR2023004922A1_(PATENT ENGLISH)_2024.pdf - Accepted Version Restricted to Repository staff only Download (98kB) | Request a copy
	PDF (Patent in Turkish (original)) 52568 NOWROOZI_ Patent_TR2023004922A1_(PATENT TURKISH)_2024.pdf - Accepted Version Restricted to Repository staff only Download (2MB) | Request a copy

Abstract

This invention relates to a deep learning-based method for enhancing computer network security using a novel 1.5C classification architecture that combines a conventional binary (2C) classifier with two one-class (1C) classifiers—each trained separately on benign and malicious samples—and fuses their outputs through a dense decision layer to improve robustness against adversarial attacks while maintaining high detection performance across N-BaIoT and RIPE-Atlas datasets.

Item Type:	Patent
Uncontrolled Keywords:	Deep learning, computer network security, adversarial attacks, 1.5C classifier, one-class classification, binary classification, convolutional neural networks (CNN), autoencoder, adversarial robustness, cyber security, machine learning security, N-BaIoT dataset, RIPE-Atlas dataset, ensemble learning, dense fusion layer, attack success rate (ASR), intrusion detection, anomaly detection.
Subjects:	H Social Sciences > HD Industries. Land use. Labor > HD61 Risk Management Q Science > Q Science (General) Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty / School / Research Centre / Research Group:	Faculty of Engineering & Science Faculty of Engineering & Science > School of Computing & Mathematical Sciences (CMS)
Last Modified:	27 Feb 2026 11:49
URI:	https://gala.gre.ac.uk/id/eprint/52568

Actions (login required)

View Item

Downloads