Ahmad Sahban Rafsanjani

Ahmad Sahban Rafsanjani

Auto-generated profile, based on publicly available information

Ahmad Sahban Rafsanjani

School of Computing and Artificial Intelligence, Faculty of Engineering and Technology, Sunway University, Bandar Sunway, Malaysia

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
7 May 2025 in Energy Informatics
Verified
Journal Article
Open access
PDF file
SASaad Aslam
Saad Aslam
PAPyi Phyo Aung
Pyi Phyo Aung
ARAhmad Sahban Rafsanjani
Ahmad Sahban Rafsanjani
ANWAR P.P. ABDUL MAJEEDANWAR P.P. ABDUL MAJEED
ANWAR P.P. ABDUL MAJEED
The paradigm shift towards Smart Grids, Smart Buildings, Smart Monitoring, and Operation has driven researchers to propose innovative solutions for designing and maintaining energy systems. Although the integration of Renewable Energy Sources (RES) supports sustainability goals, it also introduces vulnerabilities to unpredictable challenges such as grid stability, energy storage requirements, and infrastructure modernization. Machine Learning (ML) has emerged as a transformative tool to address these challenges, offering opportunities to enhance energy efficiency, and system design in alignment with Sustainable Development Goals (SDGs). The emphasis on these goals necessitates the study of new system designs that prioritize energy efficiency. Building on its proven success, researchers are increasingly adopting ML-driven approaches to accelerate advances in energy systems. This work presents a detailed review of current ML-driven research trends in energy systems, outlines the associated challenges, and provides potential research directions and recommendations. Unlike the existing literature, which focuses primarily on ML applications in the RES domain, this study offers a holistic perspective on ML-driven approaches across various aspects of energy systems, including energy policy and sustainability. It aims to serve as a comprehensive resource, bridging the gap between research advancements and practical implementations in energy systems through ML-driven innovation.

3 July 2023 in IEEE Access
Verified
Journal Article
Open access
ARAhmad Sahban Rafsanjani
Ahmad Sahban Rafsanjani
NKNorshaliza Binti Kamaruddin
Norshaliza Binti Kamaruddin
HRHazlifah Mohd Rusli
Hazlifah Mohd Rusli
MDMohammad Dabbagh
Mohammad Dabbagh
Malicious Uniform Resource Locators (URLs) are the major issue posed by cybersecurity threats. Cyberattackers spread malicious URLs to carry out attacks such as phishing and malware, which lead unsuspecting visitors into scams, resulting in monetary loss and information theft. The adoption of Quick Response (QR) codes with malicious URLs is a growing concern and is an open security issue. The existing QR link detection scanner applications mostly utilize the blacklist method to detect malicious URLs, which is not the optimal method for detecting new websites. Recently, machine learning methods have gained popularity as a means of enhancing the detection of malicious URLs. However, these methods are entirely data-dependent, and a large and updated dataset is required for the training to create an effective detection method. This research proposes QsecR, a secure and privacy-friendly QR code scanner, according to a novel malicious URL detection framework. QsecR is an Android QR code scanner based on predefined static feature classification by employing 39 classes of blacklist, lexical, host-based, and content-based features. A dataset containing 4000 real-world random URLs was gathered from URLhaus and PhishTank. The QsecR is evaluated by several QR code scanners in terms of security and privacy. The experimental result shows that QsecR outperforms others and achieves a detection accuracy of 93.50% and a precision value of 93.80%, which is significantly higher than the current secure QR code scanners. Also, QsecR is the most privacy-friendly application with the least privilege permission.

11 June 2024 in IEEE Access
Verified
Journal Article
Open access
ARAhmad Sahban Rafsanjani
Ahmad Sahban Rafsanjani
NKNorshaliza Binti Kamaruddin
Norshaliza Binti Kamaruddin
Mehran BehjatiMehran Behjati
Mehran Behjati
SASaad Aslam
Saad Aslam
ASAaliya Sarfaraz
Aaliya Sarfaraz
Angela AmphawanAngela Amphawan
Angela Amphawan
Malicious Uniform Resource Locators (URLs) pose a significant cybersecurity threat by carrying out attacks such as phishing and malware propagation. Conventional malicious URL detection methods, relying on blacklists and heuristics, often struggle to identify new and obfuscated malicious URLs. To address this challenge, machine learning and deep learning have been leveraged to enhance detection capabilities, albeit relying heavily on large and frequently updated datasets. Furthermore, the efficacy of these methods is intrinsically tied to the quality of the training data, a requirement that becomes increasingly challenging to fulfill in real-world scenarios due to constraints such as data scarcity, privacy concerns, and the dynamic nature of evolving cyber threats. In this study, we introduce an innovative framework for malicious URL detection based on predefined static feature classification by allocating priority coefficients and feature evaluation methods. Our feature classification encompasses 42 classes, including blacklist, lexical, host-based, and content-based features. To validate our framework, we collected a dataset of 5000 real-world URLs from prominent phishing and malware websites, namely URLhaus and PhishTank. We assessed our framework’s performance using three supervised machine learning methods: Support Vector Machine (SVM), Random Forest (RF), and Bayesian Network (BN). The results demonstrate that our framework outperforms these methods, achieving an impressive detection accuracy of 98.95% and a precision value of 98.60%. Furthermore, we conducted a benchmarking analysis against three comprehensive malicious URL detection methods (PDRCNN, the Li method, and URLNet), demonstrating that our proposed framework excels in terms of accuracy and precision. In conclusion, our novel malicious URL detection framework substantially enhances accuracy, significantly bolstering cybersecurity defences against emerging threats.

15 December 2025 in Digital Threats: Research and Practice
Verified
Journal Article
Open access
DJDennis Tan Jia Jun
Dennis Tan Jia Jun
ARAhmad Sahban Rafsanjani
Ahmad Sahban Rafsanjani
SASaad Aslam
Saad Aslam
Mehran BehjatiMehran Behjati
Mehran Behjati
Human factors play a critical role in enabling social engineering attacks that exploit human behaviors, cognitive biases, and psychological vulnerabilities to manipulate individuals and breach security protocols. The lack of a comprehensive understanding and effective countermeasures addressing these human factors has allowed attackers to execute successful social engineering attacks worldwide, leading to severe security breaches. According to the Internet Crime Report 2023, impersonation and business e-mail compromise are among the costliest attacks compared to other forms of cybercrimes, with both leading to the loss of 2.9 billion dollars and 1.3 billion dollars. This research article investigates the role of human factors in social engineering attacks and examines their growing prevalence and impact through real-life case studies. Additionally, it reviews various security frameworks and techniques from existing literature to identify their strengths and limitations, providing a foundation for a new conceptual security framework. To deepen our understanding of these issues, a quantitative questionnaire was conducted, collecting 208 responses to assess public knowledge, behaviors, experiences, and opinions related to human factors in information security and social engineering. The result provided several key insights such as revealing a lack of understanding of human factors and social engineering among respondents and suggesting that both technical and human aspects contribute to social engineering vulnerabilities. The findings emphasize the need for a balanced approach, leading to the proposal of a new security framework that integrates technical and human solutions to mitigate these risks effectively. By thoroughly following the framework, organizations can implement the most appropriate and effective technical and human measures, tailored to the data they have collected.