Muhammad Shafique
Papers
29
Total Citations
362
H-Index
10
About
Muhammad Shafique is a prominent researcher whose work sits at the intersection of artificial intelligence, autonomous systems, and hardware-efficient computing. His research spans several interconnected domains, including continual learning, adversarial robustness, spiking neural networks (SNNs), neuromorphic computing, and the security of cyber-physical systems. Shafique's most influential contribution examines continual learning for real-world autonomous systems, earning 106 citations and establishing a foundational framework for addressing one of AI's most persistent challenges. His investigations into adversarial attacks on camera-based systems — including physical perturbations like artificial raindrops — highlight critical vulnerabilities in deployed deep neural networks, work that has attracted significant attention with over 60 combined citations across related studies. Particularly notable is his pioneering research into neuromorphic and spiking neural network architectures for robotics and autonomous agents. Through frameworks like SNN4Agents and methodologies such as TopSpark and lpSpikeCon, Shafique advances energy-efficient, biologically-inspired intelligence suited for resource-constrained platforms. His 2024 work on embodied neuromorphic AI further positions him as a forward-thinking voice shaping the future of intelligent robotics. Collectively, his portfolio reflects a researcher deeply committed to making autonomous systems simultaneously smarter, safer, and more efficient.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5AdvRain: Adversarial Raindrops to Attack Camera-Based Smart Vision Systems19 citations · 2023
- 6
- 7
- 8
- 9
- 10SAAM: Stealthy Adversarial Attack on Monocular Depth Estimation12 citations · 2024