Shelly Wang
Papers
1
Total Citations
7
H-Index
1
About
Shelly Wang is a rising scholar at the forefront of artificial intelligence safety, specializing in the robustness of deep reinforcement learning (DRL) systems. Her research addresses a critical vulnerability in modern AI: the susceptibility of DRL policies to adversarial attacks in real-time environments. In her most-cited work, "Real-Time Adversarial Perturbations Against Deep Reinforcement Learning Policies: Attacks and Defenses" (2022, 7 citations), Wang systematically characterizes how subtle, strategically timed perturbations can derail DRL agents, and more importantly, proposes novel defense mechanisms to fortify them. This contribution is foundational for deploying DRL in high-stakes domains like autonomous driving, robotics, and cybersecurity, where reliability is paramount. While her citation count is modest, reflecting her early-career stage, the work has already garnered attention for its practical, real-world focus—bridging the gap between theoretical adversarial machine learning and applied reinforcement learning. Wang’s research signals a promising trajectory in AI safety, positioning her as a key voice in ensuring that intelligent systems remain resilient against emerging threats.
Research Focus
Key Achievements
Top Papers
- 1