Pin‐Yu Chen

Papers

Total Citations

H-Index

About

Pin‑Yu Chen is a leading researcher at the intersection of artificial intelligence, autonomous systems, and safety engineering. His work focuses on enhancing the resilience and robustness of deep learning‑driven autonomous platforms—including self‑driving cars, unmanned aerial vehicles, and robotic manipulators—against sophisticated adversarial threats. Chen’s most cited paper, “Enhanced Adversarial Strategically‑Timed Attacks against Deep Reinforcement Learning” (2020, 25 citations), introduced novel attack vectors that exploit timing vulnerabilities in DRL‑based robot learning systems, fundamentally advancing our understanding of how to stress‑test and fortify these models. In his 2022 work “Analyzing and Improving Resilience and Robustness of Autonomous Systems” (8 citations), he proposed design principles for building systems that maintain performance under unexpected perturbations. Most recently, his 2026 study “Benchmarking large language models on safety risks in scientific laboratories” (4 citations) extends his safety focus to LLMs, evaluating their reliability in high‑stakes lab environments. Chen’s contributions are pivotal for developing trustworthy AI in real‑world, safety‑critical applications, and his research continues to shape best practices for adversarial defense and system‑level robustness in autonomous technologies.