CyLab Seminar: Nicolas Papernot
August 28, 2023
12:00 p.m. ET
4th floor Panther Hollow or Zoom
*Please note this CyLab seminar is open only to Carnegie Mellon University faculty, students and staff.
Speaker: Nicolas Papernot
Assistant Professor of Computer Engineering and Computer Science, University of Toronto
Talk Title: Training Dynamics and Trust in Machine Learning
Abstract: A central question when deploying a model in the real world is, “Was our training data good enough for the real world?” In other words, what we want to know is how models change when we switch some of the training data with “other” possible options; this would allow us to understand the dependence between the model and a given dataset (i.e., the model does not change much when swapping, and hence generalizes to the other data), and how we could possibly eliminate the effects/impact of the data if we deem it to be undesirable. In this talk, we illustrate the relevance of training dynamics to trustworthy ML through the lens of three research directions: machine unlearning, model stealing defenses, and selective classification.
Bio: Nicolas Papernot is an Assistant Professor of Computer Engineering and Computer Science at the University of Toronto. He also holds a Canada CIFAR AI Chair at the Vector Institute, and a faculty affiliate at the Schwartz Reisman Institute. His research interests span the security and privacy of machine learning. Some of his group’s recent projects include proof-of-learning, collaborative learning beyond federation, dataset inference, and machine unlearning. Nicolas is an Alfred P. Sloan Research Fellow in Computer Science. His work on differentially private machine learning was awarded an outstanding paper at ICLR 2022 and a best paper at ICLR 2017. He co-created the IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) and is co-chairing its first two editions in 2023 and 2024. He previously served as an associate chair of the IEEE Symposium on Security and Privacy (Oakland), and an area chair of NeurIPS. Nicolas earned his Ph.D. at the Pennsylvania State University, working with Prof. Patrick McDaniel and supported by a Google PhD Fellowship. Upon graduating, he spent a year at Google Brain where he still spends some of his time.