Ian Goodfellow- Machine Learning Privacy and Security AIWTB 2017

Ian Goodfellow joins WTB once more for a talk on Machine Learning Privacy and Security! He is a staff research scientist at Google Brain. He is the lead author of the MIT Press textbook Deep Learning (www.deeplearningbook.org) and the inventor of generative adversarial networks. He is generally interested in all things deep learning, and usually focuses on generative models, machine learning security, and differential privacy.
To enable screen reader support, press shortcut Ctrl+Alt+Z. To learn about keyboard shortcuts, press shortcut Ctrl+slash.

From AI With the Best, online developer conference April 29-30, 2017
Check out our website: https://goo.gl/MyW3BT

https://research.google.com/teams/brain/

As machine learning algorithms become more widely used, it is important to ensure that they provide the privacy and security guarantees. In this talk, I outline some of the kinds of attacks that adversaries can make against machine learning models, and some of the defenses that we can use in response, like adversarial training and differential privacy. This talk is a high-level overview of this area to whet your appetite; AI With the Best also features detailed talks by Nicolas Papernot, Patrick McDanel and Dawn Song zooming into detail on some of these subjects.

Видео Ian Goodfellow- Machine Learning Privacy and Security AIWTB 2017 канала With The Best