Yuzhen Ding
Papers
1
Total Citations
4
H-Index
1
About
Yuzhen Ding is a researcher focused on the security and robustness of deep neural networks (DNNs), particularly in the context of adversarial machine learning. Their work addresses the critical vulnerability of DNNs to adversarial attacks—small, imperceptible perturbations that can cause models to make catastrophic errors. Ding’s most cited paper, "Evaluating a Simple Retraining Strategy as a Defense Against Adversarial Attacks" (2020, 4 citations), explores a straightforward yet effective retraining approach to bolster model resilience. This contribution is significant in a field where defenses often involve complex, computationally expensive methods. By demonstrating that even simple retraining can mitigate adversarial threats, Ding provides a practical baseline for improving DNN security in high-stakes applications like computer vision and natural language processing. While their citation count is modest, the work underscores a growing emphasis on accessible, scalable defenses. Ding’s research is particularly relevant for students and practitioners seeking to understand foundational adversarial defense mechanisms, offering a clear entry point into the ongoing battle between attack and defense in deep learning systems.
Research Focus
Key Achievements
Top Papers
- 1