Related Experiment Video
Updated: Aug 17, 2025
04:17
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
Published on: May 10, 2024
842
Fog-Assisted Deep-Learning-Empowered Intrusion Detection System for RPL-Based Resource-Constrained Smart Industries
Danish Attique1, Hao Wang2, Ping Wang2
1College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China.
Sensors (Basel, Switzerland)
|December 11, 2022
Summary
This study introduces a novel intrusion detection system (IDS) for resource-constrained smart industries, leveraging fog computing and deep learning (DL). The proposed Cu-DNNGRU framework significantly enhances security in Internet of Things (IoT) environments.
Area of Science:
- Computer Science
- Cybersecurity
- Network Engineering
Background:
- The Internet of Things (IoT) is expanding rapidly, creating smart industries but also introducing significant security vulnerabilities.
- Existing security solutions often struggle with the resource constraints inherent in many IoT sectors.
- There is a critical need for effective intrusion detection systems (IDS) tailored for these resource-limited environments.
Purpose of the Study:
- To propose a fog-assisted deep learning (DL) empowered intrusion detection system (IDS) specifically designed for resource-constrained smart industries.
- To develop and evaluate a novel framework, the Cuda-deep neural network gated recurrent unit (Cu-DNNGRU).
- To demonstrate the efficacy of the proposed IDS against state-of-the-art methods and existing literature solutions.
Main Methods:
- Developed a fog-assisted deep learning (DL) framework named Cuda-deep neural network gated recurrent unit (Cu-DNNGRU).
- Trained the Cu-DNNGRU model using the N-BaIoT dataset.
- Evaluated performance using key metrics: accuracy, precision, recall, and F1-score.
- Benchmarked Cu-DNNGRU against other advanced classifiers (Cu-LSTMDNN, Cu-BLSTM, Cu-GRU) and literature solutions.
Main Results:
- The proposed Cu-DNNGRU achieved high performance: 99.39% accuracy, 99.09% precision, 98.89% recall, and 99.21% F1-score.
- Empirical results demonstrated substantial improvements over benchmarked schemes and competitive security solutions.
- The framework showed significant strength in validating its effectiveness for IoT security.
Conclusions:
- The fog-assisted DL-empowered IDS (Cu-DNNGRU) is highly effective for securing resource-constrained smart industries.
- The proposed framework offers a robust and superior solution for intrusion detection in challenging IoT environments.
- This research contributes a validated, high-performance security mechanism for the evolving landscape of smart industries.
