Executive Briefing: Advances in privacy for machine learning systems





Level
IntermediateKatharine Jarmul sates your curiosity about how far we’ve come in implementing privacy within machine learning systems. She dives into recent advances in privacy measurements and explains how this changed the approach of privacy in machine learning. You’ll discover new techniques including differentially private data collection, federated learning, and homomorphic techniques.
She also explores why privacy has become more important since the advent of machine learning and the push that companies like Apple have put on retaining privacy for end users. You’ll approach the questions of why privacy is important now, if it’ll become more important, how this will affect the machine learning community as a whole, and other deeper questions interlaced with technical and theoretical discussion.

Katharine Jarmul
KIProtect
Katharine Jarmul is a cofounder of KIProtect and is a passionate and internationally recognized data scientist, programmer, and lecturer. Her work and research focuses on securing data for data science workflows. Previously, she held numerous roles at large companies and startups in the US and Germany, implementing data processing and machine learning systems with a focus on reliability, testability, and security. She’s an author for O‘Reilly and frequent keynote speaker at international software conferences.
Presented by
Elite Sponsors
Strategic Sponsor
Exabyte Sponsor
Impact Sponsor
Contact us
confreg@oreilly.com
For conference registration information and customer service
partners@oreilly.com
For more information on community discounts and trade opportunities with O’Reilly conferences
aisponsorships@oreilly.com
For information on exhibiting or sponsoring a conference
pr@oreilly.com
For media/analyst press inquires