Optimized deep autoencoder and BiLSTM for intrusion detection in IoTs-Fog computing

Our world is rapidly evolving toward the Internet of Things (IoT), that connects all gadgets to digital services and simplifies our lives. As IoT devices expand, network vulnerabilities may rise, leading to more network threats. An intrusion detection system (IDS) with low latency and high accuracy...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Multimedia tools and applications Ročník 84; číslo 8; s. 4907 - 4943
Hlavní autor: Alqahtani, Abdullah
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Springer US 01.03.2025
Springer Nature B.V
Témata:
Accuracy
Algorithms
Computer Communication Networks
Computer Science
Computing time
Data Structures and Information Theory
Edge computing
Error detection
Internet of Things
Intrusion detection systems
Machine learning
Multimedia Information Systems
Network latency
Optimization models
Special Purpose and Application-Based Systems
Workload
Deep learning
Multiple attack detection
Fog computing
Sparrow Search Optimization Algorithm
Intrusion detection system
Bidirectional LSTM
Internet of Things
Deep autoencoder
Hyperparameter tuning
ISSN:1573-7721, 1380-7501, 1573-7721
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Our world is rapidly evolving toward the Internet of Things (IoT), that connects all gadgets to digital services and simplifies our lives. As IoT devices expand, network vulnerabilities may rise, leading to more network threats. An intrusion detection system (IDS) with low latency and high accuracy is essential in this dynamic IoT environment to identify threats. Many IDSs utilize deep learning (DL) methods, but adjusting parameters for different environments can be challenging. This work proposes an improved hybrid Deep autoencoder (DAE) and Bidirectional long short-term memory (BiLSTM) for fog item installation to protect vital networks from prompt and efficient malicious threat detection. Determining the hyperparameters of complicated DL networks is tough. Low accuracy, efficiency, and performance in high-dimensional models afflict existing approaches. Therefore, the Sparrow Search Optimization Algorithm (SSOA) is adopted to enhance model hyperparameters. Employing IoT-based data, we assess the effectiveness of our suggested model. The outcome of the experiment obtained by analyzing the suggested IDS utilizing CICIDS2017 and BoT-IoT datasets attested to their supremacy over modern systems that are currently available in terms of precision, accuracy, FAR, error rate, and detection rate (DR). To learn more about how well our model works, added two additional metrics: Cohen's Kappa coefficients and Mathew correlation. The proposed optimization model demonstrated its ability to work well with various platforms, adapt to changing requirements, and handle larger workloads. In addition, it is possible to enhance the intrusion detection rate by minimizing both the error rate and computational time. Based on the experiments conducted, the proposed method yields superior results in terms of detection accuracy and reduced latency.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1573-7721
1380-7501
1573-7721
DOI:10.1007/s11042-024-18919-0