Papers
4
Total Citations
64
H-Index
3
About
Bassem Ouni is a leading researcher in the security of deep neural networks (DNNs) for computer vision, with a particular focus on adversarial machine learning. His work addresses the critical vulnerabilities of DNNs in safety-critical applications, such as autonomous navigation and camera-based smart systems. Ouni’s major contributions include pioneering the study of physical adversarial attacks, as evidenced by his highly cited 2023 survey (45 citations), which systematically categorizes attack trends and challenges. He has also developed novel attack methods like SAAM (Stealthy Adversarial Attack on Monocular Depth Estimation, 12 citations) and SSAP (Shape-Sensitive Adversarial Patch, 5+ citations), which demonstrate how carefully crafted perturbations can disrupt monocular depth estimation—a key task for autonomous vehicles. By exposing these weaknesses, Ouni’s work not only advances the theoretical understanding of DNN robustness but also provides practical insights for designing more secure AI systems. His research is essential reading for students and engineers working at the intersection of computer vision, security, and autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2SAAM: Stealthy Adversarial Attack on Monocular Depth Estimation12 citations · 2024
- 3
- 4