Security and Privacy of Machine Learning

Machine learning is a powerful new tool that can be used for security applications (for example, to detect malware) but machine learning itself introduces many new attack surfaces. For example, attackers can control the output of machine learning models by manipulating their inputs or training data. In this session, I give an overview of the emerging field of machine learning security and privacy.

Learning Objectives:
1: Learn about vulnerabilities of machine learning.
2: Explore existing defense techniques (differential privacy).
3: Understand opportunities to join research effort to make new defenses.



Ian Goodfellow Staff Research Scientist, Google Brain

← View more Videos

This document was retrieved from on Tue, 21 Aug 2018 23:45:35 -0400.