"How to make neural nets work, and how to make them not work"

Talk
Tom Goldstein
Talk Series: 
Time: 
09.17.2021 11:00 to 12:00
Location: 

IRB 0318

Also on Zoom: https://umd.zoom.us/j/96718034173?pwd=clNJRks5SzNUcGVxYmxkcVJGNDB4dz09 In this talk I'll survey recent work from my lab on two topics. First, I'll look at the mystery of generalization in neural nets, and possible explanations for why generalization occurs. Then I'll discuss adversarial and poisoning attacks on neural networks that cause unexpected behaviors and security vulnerabilities.