Ngai Wong
Papers
1
Total Citations
2
H-Index
1
About
Ngai Wong is a leading researcher in the fields of machine learning, computer vision, and adversarial robustness. His work critically examines the vulnerabilities of deep neural networks, particularly how small, imperceptible perturbations can fool state-of-the-art models. In his highly influential 2022 study, "What Do Adversarially Trained Neural Networks Focus: A Fourier Domain-based Study," Wong pioneered a novel Fourier-domain analysis to uncover the underlying mechanisms of adversarial training. This work revealed that adversarially robust models prioritize low-frequency features, fundamentally changing how researchers understand network focus and defense strategies. With over 2 citations and growing influence, his contributions are shaping the next generation of secure AI systems. Wong’s research not only advances theoretical understanding but also provides practical insights for building more reliable and trustworthy deep learning models, making him a key figure in the ongoing effort to bridge the gap between high performance and robust generalization.
Research Focus
Key Achievements
Top Papers
- 1