Ameya D. Patil

activity

20162021

most citedCompressing GANs using Knowledge Distillation

61 citations · 97 across the 5 of their papers we have counts for

collaborators

Showing 2021Show all

1 paper · 1 filter

cs.LG2021

Robustifying $ℓ_{\infty}$ Adversarial Training to the Union of Perturbation Models

Ameya D. Patil, Michael Tuttle, Alexander G. Schwing +1

Classical adversarial training (AT) frameworks are designed to achieve high adversarial accuracy against a single attack type, typically $ℓ_{\infty}$ norm-bounded perturbations. R…

Robustifying ℓ∞​ Adversarial Training to the Union of Perturbation Models

Robustifying $ℓ_{\infty}$ Adversarial Training to the Union of Perturbation Models