Mohammed Abuhamad
Papers
2
Total Citations
5
H-Index
2
About
Mohammed Abuhamad is an emerging researcher whose work sits at the critical intersection of deep learning security and adversarial machine learning. His research focuses on understanding and addressing the vulnerabilities inherent in deep learning models deployed in high-stakes, real-world environments, including autonomous vehicles, surveillance systems, drones, and robotics. Abuhamad's scholarship takes a rigorous multi-dimensional approach to analyzing how adversarial attacks — subtle manipulations imperceptible to the human eye — can compromise the reliability of AI systems that society increasingly depends upon. His notable publication, "Depth, Breadth, and Complexity: Ways to Attack and Defend Deep Learning Models" (2022), alongside his 2024 follow-up work on unmasking deep learning vulnerabilities, demonstrates a sustained commitment to both exposing weaknesses and developing meaningful defenses against adversarial threats. Though still accumulating citations in a competitive field, these works signal an important contribution to the growing discourse around AI safety and trustworthiness. For students and researchers working in cybersecurity, AI robustness, or safety-critical machine learning applications, Abuhamad's evolving body of work offers valuable frameworks for understanding how to build more resilient and defensible deep learning systems in an era of increasing AI adoption.
Research Focus
Key Achievements
Top Papers
- 1
- 2