Adversarial Training Reduces Information and Improves Transferability

Adversarial Training Reduces Information and Improves Transferability

22 July 2020

Alessandro Achille

Marco Maggipinto

Gian Antonio Susto

Papers citing "Adversarial Training Reduces Information and Improves Transferability"

6 / 6 papers shown

Title
Exploring the Connection between Robust and Generative Models Senad Beadini I. Masi AAML 29 1 0 08 Apr 2023
MAGIC: Mask-Guided Image Synthesis by Inverting a Quasi-Robust Classifier Mozhdeh Rouhsedaghat Masoud Monajatipoor C.-C. Jay Kuo I. Masi 34 6 0 23 Sep 2022
A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attacks Jacob Mitchell Springer Melanie Mitchell Garrett Kenyon AAML 31 43 0 03 Jun 2021
On the human-recognizability phenomenon of adversarially trained deep image classifiers Jonathan W. Helland Nathan M. VanHoudnos AAML 24 4 0 18 Dec 2020
Robustness May Be at Odds with Fairness: An Empirical Study on Class-wise Accuracy Philipp Benz Chaoning Zhang Adil Karjauv In So Kweon AAML 18 57 0 26 Oct 2020
Optimizing Information Loss Towards Robust Neural Networks Philip Sperl Konstantin Böttinger AAML 13 3 0 07 Aug 2020