Pin-Yu Chen

Dr. Pin-Yu Chen is a principal research scientist at IBM Research, serving as chief scientist for the RPI-IBM AI Research Collaboration and principal investigator for MIT-IBM Watson AI Lab projects. His work focuses on building trustworthy machine learning systems through adversarial robustness research.

His educational background includes:

• Ph.D. in Electrical Engineering and Computer Science and M.A. in Statistics from the University of Michigan, Ann Arbor (2016)
• M.S. in Communication Engineering from National Taiwan University (2011)
• B.S. in Electrical Engineering and Computer Science (Honors) from National Chiao Tung University, Taiwan (2009)

Dr. Chen's research centers on adversarial machine learning for neural network safety, with extensions to graph analytics applied in data mining and cyber security. He co-authored the book 'Adversarial Robustness for Machine Learning' and developed IBM's Adversarial Robustness Toolbox (ART) and AI Explainability 360 (AIX360) open-source libraries, establishing foundational frameworks for trustworthy AI systems.

His awards include the prestigious IJCAI Computers and Thought Award (2023), IEEE GLOBECOM 2010 Best Paper Award, UAI 2022 Best Paper Runner-Up, and multiple IBM honors including Master Inventor and Pat Goldberg Memorial Award (2022). He holds senior membership in IEEE and ACM.

As an active academic contributor, Dr. Chen serves on the Transactions on Machine Learning Research editorial board and as area chair for NeurIPS, ICML, and AAAI conferences. His 40+ U.S. patents and lectures on LLM safety risks demonstrate significant industry impact, particularly through IBM's open-source AI toolkits and MIT-IBM collaboration initiatives.