Privacy in Deployment

Patricia Thaine, Private AI, University of Toronto; Pieter Luitjens, Private AI; Dr. Parinaz Sobhani, Georgian Partners


This talk is a guide to using privacy technology in deployment. First, we will give a brief overview of the current state of privacy technology for (a) Differential Privacy & Anonymization, and (b) Secure Multiparty Computation, Homomorphic Encryption, Secure Enclaves. We will then go over the current obstacles of deploying privacy-preserving software; namely, identifying privacy risks & risk management, the capabilities & limitations of privacy tool sets and the backgrounds required to use them. Obstacles differ depending on whether one is attempting to retrofit a codebase in order to integrate privacy post-hoc or whether one is choosing the tech stack they will use for creating a codebase that integrates Privacy by Design. With those two scenarios in mind, we will discuss strategies for choosing privacy tools, for choosing to compute on the edge vs. on-premise vs. on the cloud, and for thinking about right risk management frameworks.

Patricia Thaine, Private AI, University of Toronto

Patricia Thaine is the Co-Founder and CEO of Private AI, as well as a Computer Science PhD Candidate at the University of Toronto and a Postgraduate Affiliate at the Vector Institute. Her research is focused on privacy-preserving natural language processing, machine learning, and applied cryptography. She also does research on computational methods for lost language decipherment. Patricia is a recipient of the NSERC Postgraduate Scholarship, the RBC Graduate Fellowship, the Beatrice “Trixie” Worsley Graduate Scholarship in Computer Science, and the Ontario Graduate Scholarship. She has eight years of research and software development experience, including at the McGill Language Development Lab, the University of Toronto's Computational Linguistics Lab, the University of Toronto's Department of Linguistics, and the Public Health Agency of Canada.

Pieter Luitjens, Private AI

Pieter Luitjens is the Co-Founder and CTO of Private AI. He worked on software for Mercedes-Benz and developed the first deep learning algorithms for traffic sign recognition deployed in cars made by one of the most prestigious car manufacturers in the world. He has over 10 years of engineering experience, with code deployed in multi-billion dollar industrial projects. Pieter specializes in ML edge deployment & model optimization for resource-constrained environments. He has a Bachelor of Science in Physics and Mathematics and a Bachelor of Engineering from the University of Western Australia, as well as a Masters from the University of Toronto.

Parinaz Sobhani, Georgian Partners

Parinaz Sobhani is the Director of Machine Learning on the Georgian Impact team and is responsible for leading the development of cutting-edge machine learning solutions for growth-stage startup companies.. Parinaz holds a Ph.D. from the University of Ottawa with a research focus on solving opinion mining problems using natural language processing and deep neural networks techniques. She has more than 10 years of experience in developing and designing new models and algorithms for various artificial intelligence tasks. Prior to joining Georgian Partners, Parinaz worked at Microsoft Research where she developed end-to-end neural machine translation models. She has also worked for the National Research Council of Canada, where she designed and developed deep neural network models for natural language understanding and sentiment analysis.
@inproceedings {257945,
author = {Patricia Thaine and Pieter Luitjens and Parinaz Sobhani},
title = {Privacy in Deployment},
booktitle = {2020 {USENIX} Conference on Privacy Engineering Practice and Respect ({PEPR} 20)},
year = {2020},
url = {},
publisher = {USENIX Association},
month = oct

Presentation Video