Enhancing cybersecurity using optimized anti-interference dynamic integral neural network-based intrusion detection system

Cybersecurity has become a critical concern due to the exponential growth of the Internet of Things (IoT), computer networks, and associated applications, which have introduced new vulnerabilities and increased the risk of cyberattacks. Detecting such anomalies and designing an efficient intrusion d...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Knowledge and information systems Jg. 67; H. 6; S. 5413 - 5435
Hauptverfasser: Chaudhary, Deevesh, Shekhawat, Deepika, Gupta, Sunita, Kalwar, Anju, Mishra, Neha, Nawal, Meenakshi
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Springer London 01.06.2025
Springer Nature B.V
Schlagworte:
Accuracy
Algorithms
Brief Report
Computer Science
Computing time
Cybersecurity
Data Mining and Knowledge Discovery
Database Management
Datasets
Information Storage and Retrieval
Information Systems and Communication Service
Information Systems Applications (incl.Internet)
Internet of Things
Intrusion detection systems
IT in Business
Neural networks
Optimization
Optimization algorithms
CIC IoT 2022 dataset
Industrial control systems
Anti-interference dynamic integral neural network
Smoothing–sharpening filter
Capuchin search optimization algorithm
Tyrannosaurus optimization algorithm
ISSN:0219-1377, 0219-3116
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Cybersecurity has become a critical concern due to the exponential growth of the Internet of Things (IoT), computer networks, and associated applications, which have introduced new vulnerabilities and increased the risk of cyberattacks. Detecting such anomalies and designing an efficient intrusion detection system (IDS) is essential to secure interconnected systems. Therefore, this paper proposes an enhancing cybersecurity using optimized anti-interference dynamic integral neural network-based intrusion detection system (AIDINN-CSD). Here, the input data is collected through CIC IoT 2022 dataset. The input CIC IoT 2022 dataset is preprocessed using smoothing–sharpening filter (SSF) for handling missing values and data normalization. Synthetic minority oversampling technique (SMOTE) is used for data balancing. Then, the tyrannosaurus optimization algorithm (TOA) selects relevant features from the preprocessed data. The selected features are used by anti-interference dynamic integral neural network (AIDINN) for detecting normal and attack class from the data. Then, the weight parameters of AIDINN are optimized using Capuchin search optimization algorithm (CSOA) for improving accuracy and lowering computational time. The results show that the proposed technique attains 99.23% accuracy rate, 98.97% precision and 98.47% detection rate by outperforming existing techniques. These results show the effectiveness of the AIDINN-CSD in addressing the limitations of conventional IDS, particularly its ability to handle imbalanced datasets and reduce false positives thereby offering a promising solution for enhancing IoT network security and mitigating cyber threats.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0219-1377
0219-3116
DOI:10.1007/s10115-025-02343-3