Dataset Poisoning on the Industrial Scale
A Google TechTalk, 2020/7/29, presented by Tom Goldstein, University of Maryland
ABSTRACT: Dataset poisoning is a security vulnerability in which a bad actor modifies the training data for a machine learning system in a way that allows them to control test time behavior. In this talk, I discuss our recent work on "clean-label" data poisoning methods, in which poison images appear normal to a human, and are labeled correctly. I present several ways to create such poisoning attacks, and show that they can be made effective against black-box industrial systems, including Google AutoML.
Watch video Dataset Poisoning on the Industrial Scale online without registration, duration hours minute second in high quality. This video was added by user Google TechTalks 04 June 2021, don't forget to share it with your friends and acquaintances, it has been viewed on our site 5,583 once and liked it 142 people.