J. Z. Kolter and A. Madry: Adversarial Robustness - Theory and Practice (NeurIPS 2018 Tutorial)

[@andrewstang8590]

Excellent presentation ❤❤

[@priyamdey3298]

31:09 onwards for the deeper dive

[@rainerzufall1868]

Very nice, thank you for uploading!

[@Kram1032]

This is amazing. So what would happen if you, say, repeated the Deep Dreaming experiment with a robust network like that? What I found particularly interesting about the Primate->Bird example is, that it didn't just draw in a bird anywhere into the picture. It mostly actually focused on painting out the Primate and only used that as its canvas to change stuff. The rest of the picture was relatively unaffected (as far as I could tell at least)

[@q44444q]

Excellent work and website; thank you both!

[@Kram1032]

What happens if you, instead of trying for a fixed delta, use a different delta randomly drawn at each step for optimization size? Maybe that would keep scores near 0 noise intact while still being reasonably robust, and possibly even robust against larger perturbations

[@axe863]

Neurosymbolic and Heterogenous Modalities are needed

[@anassaljarroudi2275]

25.06