ABDULBASET MUSLEH

@ibbuniv.edu.ye

Computer Sicence
IBB Univiresity

ABDULBASET MUSLEH


                           Download Compact PDF  
https://researchid.co/abdulbaset
Dr. Abdulbaset Musleh is an Assistant Professor of Computer Science and AI/ML researcher specializing in Computer Vision, Natural Language Processing, and Trustworthy AI. His work focuses on offline signature verification, phishing detection using deep learning, and AI-generated image forensics. He has published in IEEE Access and Springer and serves as a peer reviewer for international journals. His research interests include multimodal AI and deep learning applications in cybersecurity and digital forensics.

EDUCATION

Ph.D. in Computer Science, Sana’a University, Yemen (2022–2024)
M.Sc. in Computer Science, Thamar University, Yemen (2014–2017)
B.Sc. in Mathematical Computer, Ibb University, Yemen (200

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Science, Artificial Intelligence, Computer Vision and Pattern Recognition, Computer Science Applications

FUTURE PROJECTS

AI-Based Detection of Synthetic Images and Videos

Developing deep learning models for detecting AI-generated visual content using spatial, frequency, and temporal features


Applications Invited
3

Scopus Publications

29

Scholar Citations

3

Scholar h-index

1

Scholar i10-index

Scopus Publications

  • PhishingGNN: Phishing Email Detection Using Graph Attention Networks and Transformer-Based Feature Extraction
    Mejdl Safran, Abdulbaset Musleh
    IEEE Access, 2025
    Phishing emails remain a critical cybersecurity challenge, demanding detection frameworks that capture both textual semantics and structural relationships in email data. This study introduces PhishingGNN, a hybrid model that integrates DistilBERT for context-aware text analysis with Graph Attention Networks (GAT) to model email metadata and content as graph structures, detecting subtle phishing patterns overlooked by traditional methods. By transforming email bodies into relational graphs, PhishingGNN leverages Graph Neural Networks (GNNs) to analyze textual interactions while retaining computational efficiency. Evaluated on an expanded CEAS_08 dataset (39,154 samples: 17,312 non-phishing and 21,842 phishing emails), PhishingGNN achieves state-of-the-art performance: 0.9939 accuracy, balanced precision, recall, and F1-scores of 0.99, and an AUC of 1.00. Cross-dataset validation on the Nazario Corpus confirms robustness (0.9910 accuracy), outperforming contemporary few-shot learning approaches. PhishingGNN’s key innovations include a transformer-GNN architecture unifying semantic and structural reasoning, a novel graph-based email representation methodology, and comprehensive validation confirming real-world scalability. PhishingGNN advances graph-based deep learning in cybersecurity, offering a modular benchmark solution with demonstrated cross-dataset efficacy.
  • Offline Signature Verification Model Using CNN and PSO Algorithm
    Abdoulwase M. Obaid Al-Azzani, Abdulbaset M. Qaid Musleh
    Lecture Notes on Data Engineering and Communications Technologies, 2024
  • Smart System for Dengue Fever Diagnosis: A Machine Learning Approach
    Salah AL-Hagree, Khaled M. Alalayah, Nashwan Ahmed Al-Majmar, Ayedh Abdulaziz Mohsen, Amal Aqlan, Mostafa Alhel-iani, Merown Mohammed, Mohammad Albazel, Fahd Al-qasem, Motea Mohammed aljafari, Abdulbaset Musleh, Ibrahim Alnedam
    2023 3rd International Conference on Emerging Smart Technologies and Applications Esmarta 2023, 2023
    Dengue fever is a serious illness that can lead to death in areas where epidemics spread and in third world countries. Early diagnosis is crucial in preventing the severity of the disease and avoiding fatalities. To address this issue, a smart Android application has been developed that uses machine learning algorithms such as the decision tree to diagnose dengue patients. The decision tree algorithm was found to be the most accurate, with an accuracy rate of 93.7%, while other algorithms like close neighborhood had an accuracy rate of 74.29 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup> , naïve bays had an accuracy rate of 93.07%, and SVM had an accuracy rate of 68.32%. The system's response is based on specific data that is entered and processed through the decision tree algorithm. Overall, the development of this smart system can greatly improve early diagnosis of dengue fever and potentially save lives.

RECENT SCHOLAR PUBLICATIONS

  • Consensus and Gaps in AI Ethics: An Integrated Analysis of 200 Guidelines Reveals Core Principles and Emerging Themes
    A Musleh, D Alboaneen, S Alahmari, G Alshammari, E Alkayal
    2026
  • المرجع الشامل في الأعمال الإلكترونية: من التأسيس إلى التقنيات الناشئة ‎
    A Musleh
    Zenodo 1 (978-1-105-39589-5), 185 , 2026
    2026
  • PhishingGNN: Phishing Email Detection Using Graph Attention Networks and Transformer-Based Feature Extraction
    M Safran, A Musleh
    IEEE Access 13, 131390-131399 , 2025
    2025
    Citations: 3
  • Smart system for dengue fever diagnosis: A machine learning approach
    ALH Salah, KM Alalayah, NA Al-Majmar, AA Mohsen, A Aqlan, ...
    2023 3rd International Conference on Emerging Smart Technologies and … , 2023
    2023
    Citations: 6
  • Developing a model for offline signature verification using cnn architectures and genetic algorithm
    AMQ Musleh, AMO Al-Azzani
    Sana'a University Journal of Applied Sciences and Technology 1 (3) , 2023
    2023
    Citations: 6
  • A Survey on Handwritten Signature Verification Approaches
    BM Al-Maqaleh, AMQ Musleh
    Communications on Applied Electronics 4 (8), 23-29 , 2016
    2016
    Citations: 3
  • An Efficient Offline Signature Verification System using Local Features
    AMQM Basheer Mohamad Al-Maqaleh
    International Journal of Computer Applications 131 (Number 10), 39-44 , 2015
    2015
    Citations: 11
  • Year of Publication: 2015
    BM Al-Maqaleh, AMQ Musleh
    2015

MOST CITED SCHOLAR PUBLICATIONS

  • An Efficient Offline Signature Verification System using Local Features
    AMQM Basheer Mohamad Al-Maqaleh
    International Journal of Computer Applications 131 (Number 10), 39-44 , 2015
    2015
    Citations: 11
  • Smart system for dengue fever diagnosis: A machine learning approach
    ALH Salah, KM Alalayah, NA Al-Majmar, AA Mohsen, A Aqlan, ...
    2023 3rd International Conference on Emerging Smart Technologies and … , 2023
    2023
    Citations: 6
  • Developing a model for offline signature verification using cnn architectures and genetic algorithm
    AMQ Musleh, AMO Al-Azzani
    Sana'a University Journal of Applied Sciences and Technology 1 (3) , 2023
    2023
    Citations: 6
  • PhishingGNN: Phishing Email Detection Using Graph Attention Networks and Transformer-Based Feature Extraction
    M Safran, A Musleh
    IEEE Access 13, 131390-131399 , 2025
    2025
    Citations: 3
  • A Survey on Handwritten Signature Verification Approaches
    BM Al-Maqaleh, AMQ Musleh
    Communications on Applied Electronics 4 (8), 23-29 , 2016
    2016
    Citations: 3
  • Consensus and Gaps in AI Ethics: An Integrated Analysis of 200 Guidelines Reveals Core Principles and Emerging Themes
    A Musleh, D Alboaneen, S Alahmari, G Alshammari, E Alkayal
    2026
  • المرجع الشامل في الأعمال الإلكترونية: من التأسيس إلى التقنيات الناشئة ‎
    A Musleh
    Zenodo 1 (978-1-105-39589-5), 185 , 2026
    2026
  • Year of Publication: 2015
    BM Al-Maqaleh, AMQ Musleh
    2015