Eric Wong 2024 Early Career Fellow
Affiliation Assistant Professor, University of Pennsylvania Hard Problem Solved AI’s continually evolving safety and security, robustness, performance, output challenges and other shortcomings that may cause harm or erode public trust of AI systems, especially in safety-critical applications and uses where societal stakes and potential for societal harm are high.

Eric Wong is an Assistant Professor in the Department of Computer and Information Science at the University of Pennsylvania. He researches the foundations of reliable machine learning systems: understanding, debugging, and guaranteeing the behavior of data-driven models. In practice, his research empowers expert scientists and doctors to learn from AI models and make new discoveries. Eric received his Ph.D. in Machine Learning from Carnegie Mellon University, was a postdoctoral researcher at Massachusetts Institute of Technology, and is a recipient of the Siebel Scholarship, SCS Dissertation Award (honorable mention) and an Amazon Research Award, as well as paper awards at IJCNLP-AACL (area chair award) and NeurIPS workshop on ML & Security (best defense).

AI2050 Project

Generative AI is transforming science and technology with its superhuman capabilities at holding conversations, answering complex questions, and creating photo-realistic images. Unfortunately, these enhanced capabilities have also made them more dangerous: a lack of robustness has resulted in generative AI facilitating the extortion and harassment of victims, and it can share sensitive, personal data without your consent. Eric’s work develops robust machine learning methods for ensuring safe and private generative AI, to prevent the misuse of these models and hold generative AI accountable to governmental regulations.