Adversarially Robust Learning via Entropic Regularization

Gauri Jagatap, Ameya Joshi, Animesh Basak Chowdhury, Siddharth Garg, Chinmay Hegde

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper we propose a new family of algorithms, ATENT, for training adversarially robust deep neural networks. We formulate a new loss function that is equipped with an additional entropic regularization. Our loss function considers the contribution of adversarial samples that are drawn from a specially designed distribution in the data space that assigns high probability to points with high loss and in the immediate neighborhood of training samples. Our proposed algorithms optimize this loss to seek adversarially robust valleys of the loss landscape. Our approach achieves competitive (or better) performance in terms of robust classification accuracy as compared to several state-of-the-art robust learning approaches on benchmark datasets such as MNIST and CIFAR-10.

Original languageEnglish (US)
Article number780843
JournalFrontiers in Artificial Intelligence
Volume4
DOIs
StatePublished - Jan 4 2022

Keywords

  • adversarial attack
  • adversarial learning
  • neural network training
  • regularization
  • robustness

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Adversarially Robust Learning via Entropic Regularization'. Together they form a unique fingerprint.

Cite this