Ikram Benfarhat

Ikram Benfarhat

Auto-generated profile, based on publicly available information

Ikram Benfarhat

Faculty of Artificial Intelligence and Engineering, Multimedia University, Cyberjaya, Malaysia

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 January 2025 in IEEE Access
Verified
Journal Article
Open access
IBIkram Benfarhat
Ikram Benfarhat
VGVik Tor Goh
Vik Tor Goh
SLSiow Chun Lim
Siow Chun Lim
MSMuhammad Sheraz
Muhammad Sheraz
TCTeong Chee Chuah
Teong Chee Chuah
Securing data transactions across computer networks presents significant challenges, particularly concerning data privacy and cybersecurity threats. These issues are particularly critical in electric vehicle charging stations (EVCSs) due to the sensitive data involved, such as data breaches, unauthorized access, and privacy concerns. The primary challenge within EVCS architecture lies in defending against various cyberattacks. Several machine learning models, including convolutional neural networks, recurrent neural networks, and long short-term memory, have been employed to enhance EVCS security. However, these models often struggle to effectively handle the temporal dependencies, complexity, and scalability required for real-time threat detection. In this study, we propose a novel temporal convolutional network (TCN) to enhance EVCS security by rapidly detecting Open Charge Point Protocol (OCPP) attacks. Our model was trained and tested on the latest CICEVSE2024 dataset, which encompasses attacks targeting EVCS communication protocols, including OCPP and ISO15118, during charging and idle states. The proposed model achieved 100% accuracy in binary classification and five-class scenarios, and 93% accuracy in multiclass classification, surpassing existing approaches. Additionally, we conducted a comparative analysis with a hybrid model, demonstrating that the proposed TCN delivers superior performance with lower computational complexity, fewer parameters, a smaller model size, and shorter computation times. These features make the TCN model highly suitable for real-time EVCS applications. This work establishes a new benchmark for EVCS security, showcasing the potential of TCNs to deliver scalable and efficient solutions for safeguarding critical charging infrastructure against cyber threats.

9 April 2025 in IEEE Open Journal of Vehicular Technology
Verified
Journal Article
Open access
IBIkram Benfarhat
Ikram Benfarhat
VGVik Tor Goh
Vik Tor Goh
SLSiow Chun Lim
Siow Chun Lim
ILIt Ee Lee
It Ee Lee
MSMuhammad Sheraz
Muhammad Sheraz
TCTeong Chee Chuah
Teong Chee Chuah
Electric Vehicle Charging Station (EVCS) systems have become increasingly critical to the energy and transportation sectors. The detection of various attacks in EVCS, including data interception in the Open Charge Point Protocol (OCPP), poses substantial cybersecurity challenges that existing deep learning methods struggle to address effectively. This work investigates the impact of 16 types of attacks on EVCS, such as denial-of-service (DoS), reconnaissance, cryptojacking, and backdoor attacks. To address these threats, we propose an innovative model designed to identify diverse cyber threats targeting EVCS. The proposed Temporal Convolutional Network (TCN)-based Intrusion Detection System (IDS) architecture integrates four key innovations: multi-receptive fields, a gating mechanism, iterative dilation, and a self-attention mechanism combined with a Squeeze-and-Excitation (SE) block to recalibrate feature responses by explicitly modeling interactions between different channels. The proposed model effectively processes multiple temporal scales, regulates the flow of information, adapts to varying time steps, and focuses on essential components of time-series data. Experimental evaluations demonstrate that the proposed model outperforms state-of-the-art methods in terms of accuracy and detection rates across all 16 attack types in the CICEVSE2024 dataset, which comprises extensive attack vectors and variants associated with the OCPP. The proposed approach achieves higher accuracy compared to other TCN variants and exhibits high resilience against complex attacks.