On Evaluating Adversarial Robustness

CAMLIS 2019, Nicholas Carlini
On Evaluating Adversarial Robustness (abstract: www.camlis.org/2019/keynotes/...)

[@huanranchen]

So humor and excellent talk! Now I'm the fan of Nicolas Carlini

[@nabeelyoosuf]

Great talk! His comparison of current state of the robustness of ML models with the crypto in 1920's is spot on.

[@user-fy5go3rh8p]

An excellent talk, thank you!

[@narekzamanyan893]

Very informative and well-organized presentation. Thank you!!

[@ziku8910]

Great talk! About to head out and read the paper now. Thank you very much!

[@luke2642]

Great talk. It's such a difficult problem that is at the heart of generalisation. The google brain paper "Adversarial Examples that Fool both Computer
Vision and Time-Limited Humans" is worth a read.

[@ziku8910]

How did you draw the loss surface?