Federated Learning and EEL-Levy Optimization in CPS ShieldNet Fusion: A New Paradigm for Cyber–Physical Security

As cyber–physical systems are applied not only to crucial infrastructure but also to day-to-day technologies, from industrial control systems through to smart grids and medical devices, they have become very significant. Cyber–physical systems are a target for various security attacks, too; their gr...

Full description

Saved in:
Bibliographic Details
Main Authors: Nalini Manogaran, Yamini Bhavani Shankar, Malarvizhi Nandagopal, Hui-Kai Su, Wen-Kai Kuo, Sanmugasundaram Ravichandran, Koteeswaran Seerangan
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/12/3617
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850165214733926400
author Nalini Manogaran
Yamini Bhavani Shankar
Malarvizhi Nandagopal
Hui-Kai Su
Wen-Kai Kuo
Sanmugasundaram Ravichandran
Koteeswaran Seerangan
author_facet Nalini Manogaran
Yamini Bhavani Shankar
Malarvizhi Nandagopal
Hui-Kai Su
Wen-Kai Kuo
Sanmugasundaram Ravichandran
Koteeswaran Seerangan
author_sort Nalini Manogaran
collection DOAJ
description As cyber–physical systems are applied not only to crucial infrastructure but also to day-to-day technologies, from industrial control systems through to smart grids and medical devices, they have become very significant. Cyber–physical systems are a target for various security attacks, too; their growing complexity and digital networking necessitate robust cybersecurity solutions. Recent research indicates that deep learning can improve CPS security through intelligent threat detection and response. We still foresee limitations to scalability, data privacy, and handling the dynamic nature of CPS environments in existing approaches. We developed the CPS ShieldNet Fusion model as a comprehensive security framework for protecting CPS from ever-evolving cyber threats. We will present a model that integrates state-of-the-art methodologies in both federated learning and optimization paradigms through the combination of the Federated Residual Convolutional Network (FedRCNet) and the EEL-Levy Fusion Optimization (ELFO) methods. This involves the incorporation of the Federated Residual Convolutional Network into an optimization method called EEL-Levy Fusion Optimization. This preserves data privacy through decentralized model training and improves complex security threat detection. We report the results of a rigorous evaluation of CICIoT-2023, Edge-IIoTset-2023, and UNSW-NB datasets containing the CPS ShieldNet Fusion model at the forefront in terms of accuracy and effectiveness against several threats in different CPS environments. Therefore, these results underline the potential of the proposed framework to improve CPS security by providing a robust and scalable solution to current problems and future threats.
format Article
id doaj-art-854fbd10c6a64e5eb406a6474dc279c6
institution OA Journals
issn 1424-8220
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-854fbd10c6a64e5eb406a6474dc279c62025-08-20T02:21:47ZengMDPI AGSensors1424-82202025-06-012512361710.3390/s25123617Federated Learning and EEL-Levy Optimization in CPS ShieldNet Fusion: A New Paradigm for Cyber–Physical SecurityNalini Manogaran0Yamini Bhavani Shankar1Malarvizhi Nandagopal2Hui-Kai Su3Wen-Kai Kuo4Sanmugasundaram Ravichandran5Koteeswaran Seerangan6Department of Computer Science and Business Systems, S.A. Engineering College (Autonomous), Chennai 600077, Tamil Nadu, IndiaDepartment of Networking and Communications, School of Computing, College of Engineering and Technology, SRM Institute of Science and Technology (SRMIST), Kattankulathur 603203, Tamil Nadu, IndiaDepartment of Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai 600062, Tamil Nadu, IndiaDepartment of Electrical Engineering, Smart Machinery and Intelligent Manufacturing Research Center, National Formosa University, Huwei, Yunlin County 632, TaiwanDepartment of Electro-Optics Engineering, National Formosa University, Huwei, Yunlin County 632, TaiwanDepartment of Electro-Optics Engineering, National Formosa University, Huwei, Yunlin County 632, TaiwanDepartment of CSE (Artificial Intelligence and Machine Learning), S.A. Engineering College (Autonomous), Chennai 600077, Tamil Nadu, IndiaAs cyber–physical systems are applied not only to crucial infrastructure but also to day-to-day technologies, from industrial control systems through to smart grids and medical devices, they have become very significant. Cyber–physical systems are a target for various security attacks, too; their growing complexity and digital networking necessitate robust cybersecurity solutions. Recent research indicates that deep learning can improve CPS security through intelligent threat detection and response. We still foresee limitations to scalability, data privacy, and handling the dynamic nature of CPS environments in existing approaches. We developed the CPS ShieldNet Fusion model as a comprehensive security framework for protecting CPS from ever-evolving cyber threats. We will present a model that integrates state-of-the-art methodologies in both federated learning and optimization paradigms through the combination of the Federated Residual Convolutional Network (FedRCNet) and the EEL-Levy Fusion Optimization (ELFO) methods. This involves the incorporation of the Federated Residual Convolutional Network into an optimization method called EEL-Levy Fusion Optimization. This preserves data privacy through decentralized model training and improves complex security threat detection. We report the results of a rigorous evaluation of CICIoT-2023, Edge-IIoTset-2023, and UNSW-NB datasets containing the CPS ShieldNet Fusion model at the forefront in terms of accuracy and effectiveness against several threats in different CPS environments. Therefore, these results underline the potential of the proposed framework to improve CPS security by providing a robust and scalable solution to current problems and future threats.https://www.mdpi.com/1424-8220/25/12/3617cyber–physical systems (CPSs)securityfederated learningoptimizationartificial intelligence (AI)cyber threats
spellingShingle Nalini Manogaran
Yamini Bhavani Shankar
Malarvizhi Nandagopal
Hui-Kai Su
Wen-Kai Kuo
Sanmugasundaram Ravichandran
Koteeswaran Seerangan
Federated Learning and EEL-Levy Optimization in CPS ShieldNet Fusion: A New Paradigm for Cyber–Physical Security
Sensors
cyber–physical systems (CPSs)
security
federated learning
optimization
artificial intelligence (AI)
cyber threats
title Federated Learning and EEL-Levy Optimization in CPS ShieldNet Fusion: A New Paradigm for Cyber–Physical Security
title_full Federated Learning and EEL-Levy Optimization in CPS ShieldNet Fusion: A New Paradigm for Cyber–Physical Security
title_fullStr Federated Learning and EEL-Levy Optimization in CPS ShieldNet Fusion: A New Paradigm for Cyber–Physical Security
title_full_unstemmed Federated Learning and EEL-Levy Optimization in CPS ShieldNet Fusion: A New Paradigm for Cyber–Physical Security
title_short Federated Learning and EEL-Levy Optimization in CPS ShieldNet Fusion: A New Paradigm for Cyber–Physical Security
title_sort federated learning and eel levy optimization in cps shieldnet fusion a new paradigm for cyber physical security
topic cyber–physical systems (CPSs)
security
federated learning
optimization
artificial intelligence (AI)
cyber threats
url https://www.mdpi.com/1424-8220/25/12/3617
work_keys_str_mv AT nalinimanogaran federatedlearningandeellevyoptimizationincpsshieldnetfusionanewparadigmforcyberphysicalsecurity
AT yaminibhavanishankar federatedlearningandeellevyoptimizationincpsshieldnetfusionanewparadigmforcyberphysicalsecurity
AT malarvizhinandagopal federatedlearningandeellevyoptimizationincpsshieldnetfusionanewparadigmforcyberphysicalsecurity
AT huikaisu federatedlearningandeellevyoptimizationincpsshieldnetfusionanewparadigmforcyberphysicalsecurity
AT wenkaikuo federatedlearningandeellevyoptimizationincpsshieldnetfusionanewparadigmforcyberphysicalsecurity
AT sanmugasundaramravichandran federatedlearningandeellevyoptimizationincpsshieldnetfusionanewparadigmforcyberphysicalsecurity
AT koteeswaranseerangan federatedlearningandeellevyoptimizationincpsshieldnetfusionanewparadigmforcyberphysicalsecurity