
Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 127504 - 127504
Опубликована: Апрель 1, 2025
Язык: Английский
Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 127504 - 127504
Опубликована: Апрель 1, 2025
Язык: Английский
The Journal of Supercomputing, Год журнала: 2025, Номер 81(4)
Опубликована: Март 12, 2025
Язык: Английский
Процитировано
0Scientific Reports, Год журнала: 2025, Номер 15(1)
Опубликована: Март 21, 2025
Internet of Things (IoT) denotes a system interconnected devices equipped with processors, sensors, and actuators that capture exchange meaningful data other smart systems. IoT technology has been successfully applied across various sectors, including agriculture, supply chain management, education, healthcare, traffic control, utility services. However, the diverse range nodes introduces significant security challenges. Common safety features like encryption, authentication, access control frequently fall short meeting their desired functions. In this paper, we present novel perspective to by using Graph-based (GB) algorithm construct graph is evaluated graph-based learning Intrusion Detection System (IDS) incorporating Graph Attention Network (GAT). addition, leveraged small benchmark NSL-KDD dataset conduct detailed performance evaluation GNN model focusing on essential key metrics such as F1-score, recall, accuracy, precision guarantee comprehensive analysis. Our findings validate effectiveness GNN-based IDS in detecting intrusions, which highlights its robustness scalability mitigating evolving challenges within
Язык: Английский
Процитировано
0Scientific Reports, Год журнала: 2025, Номер 15(1)
Опубликована: Март 23, 2025
Abstract Detecting attacks in 5G software-defined network (SDN) environments requires a comprehensive approach that leverages traditional security measures, such as firewalls, intrusion prevention systems, and specialized techniques personalized to the unique characteristics of network. The attack detection SDN involves Machine learning (ML) Deep (DL) algorithms analyze large volumes data identify patterns indicative attacks. study’s main objective is develop an efficient DL model improve performance respond breaches effectively environment. integrates Particle Swarm Optimizer-Gated Recurrent Unit Layer-Generative Adversarial Network-Intrusion Detection System classifier (PSO-GRUGAN-IDS). PSO optimizes weight GAN backpropagation while generating synthetic (attack data) generator using GRU. discriminator uses PSO-optimized produce real forecast attack. Finally, deep classification (IDS) trained GRU with model-produced classify whether traffic malicious or normal. Moreover, this evaluated InSDN dataset compared existing model-based approaches results demonstrate significantly higher accuracy rate 98.4%, precision 98%, recall 98.5%, less time 2.464 s, lesser Log loss 1.0 more metrics instilling confidence effectiveness proposed method.
Язык: Английский
Процитировано
0Artificial Intelligence Review, Год журнала: 2025, Номер 58(7)
Опубликована: Апрель 11, 2025
Язык: Английский
Процитировано
0Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 127504 - 127504
Опубликована: Апрель 1, 2025
Язык: Английский
Процитировано
0