Predicting User Susceptibility to Social Engineering with Machine Learning
Supervisor Name
Abdallah Rashed
Supervisor Email
a.rashed@najah.edu
University
An-Najah National University
Research field
Computer Science
Bio
Abdallah Rashed earned a BSc in Computer Engineering from An-Najah National University (2008). He completed his MSc and PhD in Computer Science and Engineering at King Fahd University of Petroleum and Minerals (KFUPM) in 2018, specializing in wireless sensor network security. He has since been an Assistant Professor at An-Najah (since August 2018), with prior experience as a lecturer, instructor, and IT specialist at both institutions, including work on E-learning quality.
Conventional cybersecurity solutions focus primarily on technological safeguards while neglecting the human element. Users often fall victim to manipulative techniques due to lack of awareness, cognitive biases, or behavioral patterns. The project seeks to (1) collect demographic, behavioral, and psychological data through surveys and simulated phishing campaigns, (2) develop machine learning models capable of predicting user susceptibility, (3) analyze feature importance to understand contributing factors, and (4) provide actionable recommendations for targeted awareness programs. Data will be collected via surveys and controlled phishing simulations with volunteer participants. The dataset will be cleaned, normalized, and split into training (70%) and testing (30%) sets. Multiple machine learning algorithms including Decision Trees, Random Forests, Logistic Regression, and Neural Networks will be trained and evaluated using accuracy, precision, recall, and F1-score metrics. Feature analysis will help identify key factors affecting susceptibility.
