David Lo
Papers
3
Total Citations
14
H-Index
3
About
David Lo is a rising researcher at the forefront of artificial intelligence safety and robust decision-making. His work focuses on the critical intersection of deep learning, reinforcement learning, and software testing, with a particular emphasis on securing autonomous systems. Lo’s major contributions include pioneering “Curiosity-Driven Testing for Sequential Decision-Making Processes,” a novel framework that enhances the reliability of AI in high-stakes domains like autonomous driving and robotic control. He is also the lead author of the BAFFLE system, which exposes and defends against hidden backdoor attacks in offline reinforcement learning datasets—a groundbreaking contribution to AI security. With his most-cited papers accumulating over 14 citations since 2022, Lo’s research is already shaping how the community addresses vulnerabilities in learning-based systems. His work on BAFFLE, presented in both 2022 and 2024, has been recognized for its dual focus on attack and defense, making it a key reference for researchers in trustworthy AI. For students and scholars exploring the safety of sequential decision-making, David Lo’s research offers essential insights into building more resilient and secure intelligent agents.
Research Focus
Key Achievements
Top Papers
- 1Curiosity-Driven Testing for Sequential Decision-Making Process6 citations · 2024
- 2Baffle: Hiding Backdoors in Offline Reinforcement Learning Datasets5 citations · 2024
- 3BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets3 citations · 2022