Portfolio & Research
Ph.D. Candidate, Electrical Engineering
Electrical and computer engineer and Ph.D. researcher applying deep learning to vulnerability detection in software and hardware systems. I bridge rigorous analysis with real-world engineering impact.
Institution
North Carolina A&T State University, College of Engineering
Department
Electrical & Computer Engineering
Research Focus
Vulnerability detection using Deep Learning Applications
Advisor
Dr Ahmad Patooghy
myndebugre@aggies.ncat.edu
I am a Ph.D. candidate in Electrical and Computer Engineering, with a dissertation focused on deep learning approaches to vulnerability detection across software and hardware systems — building graph-based neural methods that detect, explain, and help repair vulnerabilities in source code and digital hardware, with applications to safety-critical and cyber-physical systems.
My academic journey began with a B.S. in Telecommunication Engineering at the Kwame Nkrumah University of Science and Technology, followed by an M.S. in Electronics and Communication Engineering at the Yildiz Technical University. I have since been involved in federally funded research projects and industry collaborations, developing robust simulation frameworks and analyzing complex multi-physics phenomena.
Outside of research, I am passionate about science communication, mentoring junior engineers, and I believe in making rigorous engineering tools accessible to a broader community.
Autonomous Mobile Robots
Simulation and analysis of autonomous robot navigation, path planning, and obstacle avoidance across multiple scenarios.
5 simulations
Linear Control
Design and simulation of linear control strategies including PID, state-space, and frequency-domain analysis across multiple plant models.
6 simulations
Digital Signal Processing
Circuit-level DSP implementations in MATLAB. Eight circuits designed from component values to simulation, covering signal generation through sampling theory.
9 simulations
Peer-reviewed publications and preprints. Click a paper to access the full document.
An interactive map of CWE-1194 (Hardware Design), MITRE's taxonomy of hardware-level security weaknesses spanning privilege separation, physical side channels, debug and test interfaces, and transient-execution exposure. Built as part of ongoing work on graph-based vulnerability modeling and threat taxonomy development for hardware and multi-agent AI security.
CWE-1194 · Hardware Design
Click a category to expand it, click any node for detail, or search by CWE ID. Opens in a new tab.