Nicolas Papernot

Faculty Member

Assistant Professor, Department of Electrical & Computer Engineering, Faculty of Applied Science & Engineering, University of Toronto

Assistant Professor, Department of Computer Science, Faculty of Arts & Science, University of Toronto

Canada CIFAR Artificial Intelligence Chair

Faculty Affiliate, Schwartz Reisman Institute for Technology and Society

Alfred P. Sloan Research Fellow in Computer Science.

Nicolas Papernot is an Assistant Professor in the Department of Electrical and Computer Engineering and the Department of Computer Science at the University of Toronto. He is also a faculty member at the Vector Institute where he holds a Canada CIFAR AI Chair, and a faculty affiliate at the Schwartz Reisman Institute. His research interests span the security and privacy of machine learning. Nicolas is a Connaught Researcher and was previously a Google PhD Fellow. His work on differentially private machine learning received a best paper award at ICLR 2017. He is an associate chair of IEEE S&P (Oakland) and an area chair of NeurIPS. He earned his Ph.D. at the Pennsylvania State University, working with Prof. Patrick McDaniel. Upon graduating, he spent a year as a research scientist at Google Brain where he still spends some of his time.

Professor Papernot’s research interests span the areas of computer security, privacy, and machine learning. Together with his collaborators, he demonstrated the first practical black-box attacks against deep neural networks. His work on differential privacy for machine learning, involving the development of a family of algorithms called Private Aggregation of Teacher Ensembles (PATE), has made it easy for machine learning researchers to contribute to differential privacy research. He also co-authored with Ian Goodfellow an open-source library called CleverHans, now widely adopted in the technical community to benchmark machine learning in adversarial settings.

Research Interests

  • Computer Security
  • Machine Learning
  • Privacy

Highlights

  • Alfred P. Sloan Research Fellow in Computer Science
  • Connaught New Researcher Award
  • Google PhD Fellowship in Security
  • Best Paper Award (5th International Conference on Learning Representations)

Publications

Dataset Inference: Ownership Resolution in Machine Learning

Pratyush Maini and Mohammad Yaghini and Nicolas Papernot

2021

Bad characters: Imperceptible nlp attacks

Nicholas Boucher and Ilia Shumailov and Ross Anderson and Nicolas Papernot

2021

Manipulating SGD with data ordering attacks

Ilia Shumailov and Zakhar Shumaylov and Dmitry Kazhdan and Yiren Zhao and Nicolas Papernot and Murat A Erdogdu and Ross Anderson

2021

Hyperparameter Tuning with Renyi Differential Privacy

Nicolas Papernot and Thomas Steinke

2021

On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning

Anvith Thudi and Hengrui Jia and Ilia Shumailov and Nicolas Papernot

2021

Markpainting: Adversarial Machine Learning meets Inpainting

David Khachaturov and Ilia Shumailov and Yiren Zhao and Nicolas Papernot and Ross Anderson

2021

Unrolling sgd: Understanding factors influencing machine unlearning

Anvith Thudi and Gabriel Deza and Varun Chandrasekaran and Nicolas Papernot

2021

Increasing the Cost of Model Extraction with Calibrated Proof of Work

Adam Dziedzic and Muhammad Ahmad Kaleem and Yu Shen Lu and Nicolas Papernot

2022

Accelerating Symbolic Analysis for Android Apps

Mingyue Yang and David Lie and Nicolas Papernot

2021

Losing Less: A Loss for Differentially Private Deep Learning

Ali Shahin Shamsabadi and Nicolas Papernot

2021

A Zest of LIME: Towards Architecture-Independent Model Distances

Hengrui Jia and Hongyu Chen and Jonas Guan and Ali Shahin Shamsabadi and Nicolas Papernot

2021

Private Multi-Winner Voting For Machine Learning

Adam Dziedzic and Christopher A Choquette-Choo and Natalie Dullerud and Vinith Menon Suriyakumar and Ali Shahin Shamsabadi and Muhammad Ahmad Kaleem and Somesh Jha and Nicolas Papernot and Xiao Wang

2021

Context-invariant, multi-variate time series representations

Stephan Rabanser and Tim Januschowski and Kashif Rasul and Oliver Borchert and Richard Kurle and Jan Gasthaus and Michael Bohlke-Schneider and Nicolas Papernot and Valentin Flunkert

2021

Fourth International Workshop on Dependable and Secure Machine Learning–DSML 2021

Hui Xu and Guanpeng Li and Homa Alemzadeh and Rakesh Bobba and Varun Chandrasekaran and David E Evans and Nicolas Papernot and Karthik Pattabiraman and Florian Tramer

2021

Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning

Natalie Dullerud and Karsten Roth and Kimia Hamidieh and Nicolas Papernot and Marzyeh Ghassemi

2019