Dian Hong
Papers
1
Total Citations
3
H-Index
1
About
Dian Hong is a researcher focused on the security and robustness of artificial intelligence systems, particularly within the domain of robot vision. Her work addresses the critical vulnerability of vision models to adversarial examples—subtle, often imperceptible perturbations that can cause models to make erroneous decisions. In her most cited paper, "Attacking Robot Vision Models Efficiently Based on Improved Fast Gradient Sign Method" (2024), she introduces RMS-FGSM, an advanced adversarial attack algorithm designed to efficiently expose weaknesses in robot perception systems. This contribution is vital for developing more secure and reliable autonomous systems. While her citation count is still growing, her research has immediate relevance to the safety of real-world robotics applications, from autonomous navigation to industrial automation. By probing the stability of these models, Hong is helping to lay the groundwork for more resilient AI, ensuring that robots can perceive and interpret their environments correctly even under adversarial conditions.
Research Focus
Key Achievements
Top Papers
- 1