Adversarial Machine Learning

8 926
13.5
Опубликовано 21 ноября 2019, 1:22
The reliability of machine learning systems in the presence of adversarial noise has become a major field of study in recent years. As ML is being used for increasingly security sensitive applications and is trained in increasingly unreliable data, the ability for learning algorithms to tolerate worst-case noise has become more and more important. In this talk, I'll survey a number of recent results in this area, both theoretical and more applied. We will survey recent advances in robust statistics, data poisoning, and adversarial examples for neural networks. The overarching goal is to give provably robust algorithms for these problems, which still perform well in practice.

Talk slides: microsoft.com/en-us/research/u...

See more on this and other talks at Microsoft Research: microsoft.com/en-us/research/v...
Свежие видео
6 дней – 431:13:03
MPI+ Applications on AMD GPUs
6 дней – 12 1911:13
Tested for Everyday Life | Samsung
12 дней – 1587:44
Why is my Amazon ECS task stopped?
13 дней – 5 2231:33
Get started with Microsoft Whiteboard
автотехномузыкадетское