Speaker: Satish Shankar
This talk will introduce the essential concepts from cryptography necessary to build AI systems that use sensitive data and yet protect our privacy. Specifically, we will cover concepts from secure multi-party computation (MPC) and how they can be used to build machine learning algorithms.
Why does this matter? This matters because we as a society are struggling to balance the benefits of data driven systems and the privacy risks they create. Building any machine learning or analytics model necessitates the collection of data. If this data is sensitive or personal, it inevitably turns into an honeypot for hackers. At a societal level, we are responding to this issue by introducing more regulation such as the GDPR.
Instead of regulations, it is possible to use cryptography to protect our data and still analyse it: This talk show how.
About: Shankar leads the machine learning and AI efforts for Manulife’s innovation labs. He works on quantitative investment and insurance, drawing on a wide range of fields from machine learning, natural language processing, differential privacy, encryption, and more.
He is particularly interested in the intersection of blockchains, distributed systems and privacy in machine learning.
Event Page: https://www.meetup.com/Singapore-Python-User-Group/events/249344900/
Produced by Engineers.SG
Help us caption & translate this video!