Muhammad Abdullah Hanif
Papers
10
Total Citations
200
H-Index
5
About
Muhammad Abdullah Hanif is a leading researcher at the intersection of trustworthy artificial intelligence and autonomous systems, with a primary focus on adversarial machine learning and robust perception for real-world deployment. His work systematically exposes critical vulnerabilities in deep neural networks used in safety-critical applications, particularly in camera-based smart systems for autonomous vehicles and robotics. He has pioneered research on physical adversarial attacks, including the development of AdvRain, a framework that uses adversarial raindrops to deceive vision systems, and SAAM, a stealthy attack on monocular depth estimation. His comprehensive survey on physical adversarial attacks (45 citations) has become a key reference in the field, while his work on continual learning for autonomous systems (106 citations) addresses the fundamental challenge of adapting models to non-stationary environments. Hanif also contributes to practical deployment challenges, proposing cross-layer optimizations for efficient deep learning inference on resource-constrained edge platforms. His recent work on curiosity-driven reinforcement learning for quadruped locomotion and open-world object detection demonstrates a commitment to advancing autonomous capabilities beyond traditional benchmarks. With over 200 total citations and a rapidly growing publication record, Hanif is establishing himself as a significant voice in building secure, adaptive, and efficient AI for the real world.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3AdvRain: Adversarial Raindrops to Attack Camera-Based Smart Vision Systems19 citations · 2023
- 4SAAM: Stealthy Adversarial Attack on Monocular Depth Estimation12 citations · 2024
- 5
- 6
- 7A Framework for Open World Object Detection2 citations · 2023
- 8
- 9
- 10