Transfer learning for securing electric vehicle charging infrastructure from cyber-physical attacks

Abstract Electric Vehicle Charging Station (EVCS) security is a growing concern in today’s connected world due to the growing complexity and frequency of cyber threats. Traditional Intrusion Detection Systems (IDS) for EV chargers struggle to detect novel or unexpected attacks due to their usage of...

Full description

Saved in:
Bibliographic Details
Main Authors: Ahmad Almadhor, Shtwai Alsubai, Imen Bouazzi, Vincent Karovic, Monika Davidekova, Abdullah Al Hejaili, Gabriel Avelino Sampedro
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-93135-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849390341657985024
author Ahmad Almadhor
Shtwai Alsubai
Imen Bouazzi
Vincent Karovic
Monika Davidekova
Abdullah Al Hejaili
Gabriel Avelino Sampedro
author_facet Ahmad Almadhor
Shtwai Alsubai
Imen Bouazzi
Vincent Karovic
Monika Davidekova
Abdullah Al Hejaili
Gabriel Avelino Sampedro
author_sort Ahmad Almadhor
collection DOAJ
description Abstract Electric Vehicle Charging Station (EVCS) security is a growing concern in today’s connected world due to the growing complexity and frequency of cyber threats. Traditional Intrusion Detection Systems (IDS) for EV chargers struggle to detect novel or unexpected attacks due to their usage of predetermined signatures and limited detection capabilities. Existing EV charging station security systems are unable to identify many known and undiscovered threats since they primarily rely on feature selection and categorization accuracy. It is common for these systems to be constructed using conventional machine learning algorithms. So many common signs of attacks are ignored. This paper proposes a Transfer learning (TL) framework for cyber-physical attack detection in EVCS in order to overcome these difficulties and improve both accuracy and scalability. The weights preserved from the Deep Neural Network (DNN) model after implementing data normalization and min-max scaling techniques utilized for training are used to initialize a new model termed Transfer Learning. The study also provides a comparison with different DL models such as Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNN), Long Short-Term Memory-Recurrent Neural Networks (LSTM-RNN), and Gated Recurrent Unit (GRU). The CICEVSE2024 (EVSE-A and EVSE-B) datasets are used to assess the framework, where one dataset is used to train and store weights, and the second is used to evaluate the learned patterns using transfer learning. Several evaluation matrices are used to evaluate the suggested model. The experimental results demonstrate that the TL model attained 93% accuracy. Consequently, the pre-train TL model provides a high degree of symmetry between EVCS security and the detection of malicious attacks.
format Article
id doaj-art-e8d81ccc93214c01abafa3becf8b7e61
institution Kabale University
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-e8d81ccc93214c01abafa3becf8b7e612025-08-20T03:41:41ZengNature PortfolioScientific Reports2045-23222025-03-0115112010.1038/s41598-025-93135-wTransfer learning for securing electric vehicle charging infrastructure from cyber-physical attacksAhmad Almadhor0Shtwai Alsubai1Imen Bouazzi2Vincent Karovic3Monika Davidekova4Abdullah Al Hejaili5Gabriel Avelino Sampedro6Department of Computer Engineering and Networks, College of Computer and Information Sciences, Jouf UniversityCollege of Computer Engineering and Sciences, Prince Sattam bin Abdulaziz UniversityDepartment of Industrial Engineering, College of Engineering, King Khalid UniversityDepartment of Information Management and Business Systems, Faculty of Management, Comenius University in BratislavaDepartment of Information Management and Business Systems, Faculty of Management, Comenius University in BratislavaFaculty of Computers and Information Technology, Computer Science Department, University of TabukDepartment of Computer Science, University of the Philippines DilimanAbstract Electric Vehicle Charging Station (EVCS) security is a growing concern in today’s connected world due to the growing complexity and frequency of cyber threats. Traditional Intrusion Detection Systems (IDS) for EV chargers struggle to detect novel or unexpected attacks due to their usage of predetermined signatures and limited detection capabilities. Existing EV charging station security systems are unable to identify many known and undiscovered threats since they primarily rely on feature selection and categorization accuracy. It is common for these systems to be constructed using conventional machine learning algorithms. So many common signs of attacks are ignored. This paper proposes a Transfer learning (TL) framework for cyber-physical attack detection in EVCS in order to overcome these difficulties and improve both accuracy and scalability. The weights preserved from the Deep Neural Network (DNN) model after implementing data normalization and min-max scaling techniques utilized for training are used to initialize a new model termed Transfer Learning. The study also provides a comparison with different DL models such as Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNN), Long Short-Term Memory-Recurrent Neural Networks (LSTM-RNN), and Gated Recurrent Unit (GRU). The CICEVSE2024 (EVSE-A and EVSE-B) datasets are used to assess the framework, where one dataset is used to train and store weights, and the second is used to evaluate the learned patterns using transfer learning. Several evaluation matrices are used to evaluate the suggested model. The experimental results demonstrate that the TL model attained 93% accuracy. Consequently, the pre-train TL model provides a high degree of symmetry between EVCS security and the detection of malicious attacks.https://doi.org/10.1038/s41598-025-93135-wElectric vehicle charging stationsCyber attacksDeep learningTransfer learningLSTM-RNNIntrusion detection systems (IDS)
spellingShingle Ahmad Almadhor
Shtwai Alsubai
Imen Bouazzi
Vincent Karovic
Monika Davidekova
Abdullah Al Hejaili
Gabriel Avelino Sampedro
Transfer learning for securing electric vehicle charging infrastructure from cyber-physical attacks
Scientific Reports
Electric vehicle charging stations
Cyber attacks
Deep learning
Transfer learning
LSTM-RNN
Intrusion detection systems (IDS)
title Transfer learning for securing electric vehicle charging infrastructure from cyber-physical attacks
title_full Transfer learning for securing electric vehicle charging infrastructure from cyber-physical attacks
title_fullStr Transfer learning for securing electric vehicle charging infrastructure from cyber-physical attacks
title_full_unstemmed Transfer learning for securing electric vehicle charging infrastructure from cyber-physical attacks
title_short Transfer learning for securing electric vehicle charging infrastructure from cyber-physical attacks
title_sort transfer learning for securing electric vehicle charging infrastructure from cyber physical attacks
topic Electric vehicle charging stations
Cyber attacks
Deep learning
Transfer learning
LSTM-RNN
Intrusion detection systems (IDS)
url https://doi.org/10.1038/s41598-025-93135-w
work_keys_str_mv AT ahmadalmadhor transferlearningforsecuringelectricvehiclecharginginfrastructurefromcyberphysicalattacks
AT shtwaialsubai transferlearningforsecuringelectricvehiclecharginginfrastructurefromcyberphysicalattacks
AT imenbouazzi transferlearningforsecuringelectricvehiclecharginginfrastructurefromcyberphysicalattacks
AT vincentkarovic transferlearningforsecuringelectricvehiclecharginginfrastructurefromcyberphysicalattacks
AT monikadavidekova transferlearningforsecuringelectricvehiclecharginginfrastructurefromcyberphysicalattacks
AT abdullahalhejaili transferlearningforsecuringelectricvehiclecharginginfrastructurefromcyberphysicalattacks
AT gabrielavelinosampedro transferlearningforsecuringelectricvehiclecharginginfrastructurefromcyberphysicalattacks