Fractional Artificial Protozoa Optimization Enabled Deep Learning for Intrusion Detection and Mitigation in Cyber-Physical Systems
Cyber-physical systems (CPSs) have a prominent role in real-time applications by means of deep integration of computing, control technologies, and communication. CPSs are gradually growing and utilized in important infrastructure and industries for attaining smart grid, smart transportation, and sma...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10802868/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850120929372274688 |
|---|---|
| author | Shaik Abdul Rahim Arun Manoharan |
| author_facet | Shaik Abdul Rahim Arun Manoharan |
| author_sort | Shaik Abdul Rahim |
| collection | DOAJ |
| description | Cyber-physical systems (CPSs) have a prominent role in real-time applications by means of deep integration of computing, control technologies, and communication. CPSs are gradually growing and utilized in important infrastructure and industries for attaining smart grid, smart transportation, and smart healthcare, which assists governments and citizens. Nevertheless, the network and wireless communication technology creates high complexity, and the intelligence and dynamic of network intrusions make CPS more insecure to network intrusions and provide more critical threats to human life and national security. Therefore, a framework for intrusion detection and mitigation in CPS is developed to overcome the above issues using Fractional Artificial Protozoa Optimization enabled Spiking VGG-16 (FAPO Spiking VGG-16). First, the CPSs module is initialized, and then the attack mitigation is carried out. The input log file from the database is normalized using Quantile Normalization (QN). Afterwards, features are selected employing the Skill Optimization Algorithm (SOA). Thereafter, intrusion detection is carried out with Spiking VGG-16. Lastly, attack classification is accomplished utilizing Spiking VGG-16 trained by FAPO, and then attack mitigation is detected. The metrics like Accuracy, Precision, Recall, F1-Score, Matthew’s correlation coefficient (MCC), and Memory acquired 92.454%, 91.858%, 90.660%, 91.224%, 91.650%, and 1.541 MB. |
| format | Article |
| id | doaj-art-38cd44dd5d654d8d960a69c8057bbf22 |
| institution | OA Journals |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-38cd44dd5d654d8d960a69c8057bbf222025-08-20T02:35:15ZengIEEEIEEE Access2169-35362024-01-011219407719409010.1109/ACCESS.2024.351808910802868Fractional Artificial Protozoa Optimization Enabled Deep Learning for Intrusion Detection and Mitigation in Cyber-Physical SystemsShaik Abdul Rahim0https://orcid.org/0009-0001-7474-9976Arun Manoharan1https://orcid.org/0000-0003-1552-9970Department of Embedded Technology, School of Electronic Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, IndiaDepartment of Embedded Technology, School of Electronic Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, IndiaCyber-physical systems (CPSs) have a prominent role in real-time applications by means of deep integration of computing, control technologies, and communication. CPSs are gradually growing and utilized in important infrastructure and industries for attaining smart grid, smart transportation, and smart healthcare, which assists governments and citizens. Nevertheless, the network and wireless communication technology creates high complexity, and the intelligence and dynamic of network intrusions make CPS more insecure to network intrusions and provide more critical threats to human life and national security. Therefore, a framework for intrusion detection and mitigation in CPS is developed to overcome the above issues using Fractional Artificial Protozoa Optimization enabled Spiking VGG-16 (FAPO Spiking VGG-16). First, the CPSs module is initialized, and then the attack mitigation is carried out. The input log file from the database is normalized using Quantile Normalization (QN). Afterwards, features are selected employing the Skill Optimization Algorithm (SOA). Thereafter, intrusion detection is carried out with Spiking VGG-16. Lastly, attack classification is accomplished utilizing Spiking VGG-16 trained by FAPO, and then attack mitigation is detected. The metrics like Accuracy, Precision, Recall, F1-Score, Matthew’s correlation coefficient (MCC), and Memory acquired 92.454%, 91.858%, 90.660%, 91.224%, 91.650%, and 1.541 MB.https://ieeexplore.ieee.org/document/10802868/Artificial protozoa optimizationattack mitigationcyber-physical systemsfractional conceptintrusion detection |
| spellingShingle | Shaik Abdul Rahim Arun Manoharan Fractional Artificial Protozoa Optimization Enabled Deep Learning for Intrusion Detection and Mitigation in Cyber-Physical Systems IEEE Access Artificial protozoa optimization attack mitigation cyber-physical systems fractional concept intrusion detection |
| title | Fractional Artificial Protozoa Optimization Enabled Deep Learning for Intrusion Detection and Mitigation in Cyber-Physical Systems |
| title_full | Fractional Artificial Protozoa Optimization Enabled Deep Learning for Intrusion Detection and Mitigation in Cyber-Physical Systems |
| title_fullStr | Fractional Artificial Protozoa Optimization Enabled Deep Learning for Intrusion Detection and Mitigation in Cyber-Physical Systems |
| title_full_unstemmed | Fractional Artificial Protozoa Optimization Enabled Deep Learning for Intrusion Detection and Mitigation in Cyber-Physical Systems |
| title_short | Fractional Artificial Protozoa Optimization Enabled Deep Learning for Intrusion Detection and Mitigation in Cyber-Physical Systems |
| title_sort | fractional artificial protozoa optimization enabled deep learning for intrusion detection and mitigation in cyber physical systems |
| topic | Artificial protozoa optimization attack mitigation cyber-physical systems fractional concept intrusion detection |
| url | https://ieeexplore.ieee.org/document/10802868/ |
| work_keys_str_mv | AT shaikabdulrahim fractionalartificialprotozoaoptimizationenableddeeplearningforintrusiondetectionandmitigationincyberphysicalsystems AT arunmanoharan fractionalartificialprotozoaoptimizationenableddeeplearningforintrusiondetectionandmitigationincyberphysicalsystems |