A Machine Learning-Based Intrusion Detection System for IoT Electric Vehicle Charging Stations (EVCSs)

ElKashlan, Mohamed; Elsayed, Mahmoud Said; Jurcut, Anca Delia; Azer, Marianne A.

doi:10.3390/electronics12041044

Cited by 29 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, the application of ML techniques specifically for detecting distributed denialof-service (DDoS) attacks in EVCS networks is another notable research area [20,21]. Existing research efforts focus on comparing various ML classifiers to identify the most effective methods for maintaining the stability and security of EVCS within smart city infrastructures.…”

Section: Related Workmentioning

confidence: 99%

Next–Generation Intrusion Detection for IoT EVCS: Integrating CNN, LSTM, and GRU Models

Kilichev,

Turimov,

Kim

2024

Mathematics

View full text Add to dashboard Cite

In the evolving landscape of Internet of Things (IoT) and Industrial IoT (IIoT) security, novel and efficient intrusion detection systems (IDSs) are paramount. In this article, we present a groundbreaking approach to intrusion detection for IoT-based electric vehicle charging stations (EVCS), integrating the robust capabilities of convolutional neural network (CNN), long short-term memory (LSTM), and gated recurrent unit (GRU) models. The proposed framework leverages a comprehensive real-world cybersecurity dataset, specifically tailored for IoT and IIoT applications, to address the intricate challenges faced by IoT-based EVCS. We conducted extensive testing in both binary and multiclass scenarios. The results are remarkable, demonstrating a perfect 100% accuracy in binary classification, an impressive 97.44% accuracy in six-class classification, and 96.90% accuracy in fifteen-class classification, setting new benchmarks in the field. These achievements underscore the efficacy of the CNN-LSTM-GRU ensemble architecture in creating a resilient and adaptive IDS for IoT infrastructures. The ensemble algorithm, accessible via GitHub, represents a significant stride in fortifying IoT-based EVCS against a diverse array of cybersecurity threats.

show abstract

Section: Related Workmentioning

confidence: 99%

Next–Generation Intrusion Detection for IoT EVCS: Integrating CNN, LSTM, and GRU Models

Kilichev,

Turimov,

Kim

2024

Mathematics

View full text Add to dashboard Cite

show abstract

“…In study [2], the authors proposed an intrusion detection system using deep belief network (DBN). DBN is an algorithm for increasing the number of different unsupervised networks grouped together to serve as input for the next layer.…”

Section: Literature Reviewmentioning

confidence: 99%

Enhancing Cybersecurity through GAN-Augmented and Hybrid Feature Selection Machine Learning Models: A Case Study on EVSE Data

Tanyıldız,

Batur Şahin,

Batur Dinler

2024

NATURENGS MTU Journal of Engineering and Natural Sciences Malatya Turgut Ozal University

View full text Add to dashboard Cite

Electric Vehicle Charging Stations (EVCSs) are critical components of modern transportation infrastructure. However, smart grid integrations create new security vulnerabilities. Cyber attacks can damage EVCSs, cause financial losses, and compromise user security. Traditional security measures are not enough. By analyzing the large data sets produced by EVCSs, machine learning (ML) can detect anomalies and provide predictive maintenance. The increasing importance of EVCSs in smart grid infrastructure necessitates taking advanced security measures. Machine learning-based intrusion detection systems represent a promising solution to the dynamic and complex cyber threats facing these critical infrastructures. Through continuous learning and adaptation, ML can provide a robust defense mechanism that ensures the security and reliability of EVCSs in the face of evolving cyber threats.

show abstract

“…The proposed EDS drives both BLDC motors with a set of "averaged" signals based on the strategy shown in Figure 5 by synchronizing/locking the rotor angle and speed of the motors if required. The improved EDS differs from a soft-lock approach and conventional designs, which employ a classic PI speed controller for the traction motors through Hall sensor signals [13][14][15][16][17][18][19][20].…”

Section: Eds Modelmentioning

confidence: 99%

“…With simulation tools, researchers can implement an enormous number of implementations on any DT, which is difficult on a physical asset. The DT performs as a desired platform along with IoT architectures to map the offline physical device to a DT model [20]. With the large amount of sensory information that an EV's drive system produces, DT technology is considerably more appealing than other tools such as hardware-in-the-loop evaluations.…”

Section: Introductionmentioning

confidence: 99%

A Digital Twinning Approach for the Internet of Unmanned Electric Vehicles (IoUEVs) in the Metaverse

et al. 2023

View full text Add to dashboard Cite

Regarding the importance of the Internet of Things (IoT) and the Metaverse as two practical emerging technologies to enhance the digitalization of public transportation systems, this article introduces an approach for the improvement of IoT and unmanned electric vehicles in the Metaverse, called the Internet of Unmanned Electric Vehicles (IoUEVs). This research includes two important contributions. The first contribution is the description of a framework for how unmanned electric vehicles can be used in the Metaverse, and the second contribution is the creation of a digital twin for an unmanned electric vehicle. In the digital twin section, which is the focus of this research, we present a digital twin of an electronic differential system (EDS) in which the stability has been improved. Robust fuzzy logic algorithm-based speed controllers are employed in the EDS to independently control the EV wheels driven by high-performance brushless DC (BLDC) electric motors. In this study, the rotor position information of the motors, which is estimated from the low-precision Hall-effect sensors mounted on the motors’ shafts, is combined and converted to a set of common switching signals for empowering the EDS of the electric vehicle traction drive system. The proposed digital twin EDS relies on an accurate Hall sensor signals-based synchronizing/locking strategy with a dynamic steering pattern capable of running in severe road conditions with different surface profiles to ensure the EV’s stability. Unlike recent EDSs, the proposed digital twinning approach includes a simple practical topology with no need for auxiliary infrastructures, which is able to reduce mechanical losses and stresses and can be adapted to IoUEVs more effectively.

show abstract

A Machine Learning-Based Intrusion Detection System for IoT Electric Vehicle Charging Stations (EVCSs)

Cited by 29 publications

References 24 publications

Next–Generation Intrusion Detection for IoT EVCS: Integrating CNN, LSTM, and GRU Models

Next–Generation Intrusion Detection for IoT EVCS: Integrating CNN, LSTM, and GRU Models

Enhancing Cybersecurity through GAN-Augmented and Hybrid Feature Selection Machine Learning Models: A Case Study on EVSE Data

A Digital Twinning Approach for the Internet of Unmanned Electric Vehicles (IoUEVs) in the Metaverse

Contact Info

Product

Resources

About