Deep Learning Architectures for Robust Classification under Adversarial Noise

Abstract

The objective of this DARPA study is to develop deep neural network (DNN) architectures that can classify images with a provably robust accuracy despite adversarial noise.

Document Details

Document Type
DoD Grant Award
Publication Date
Jul 29, 2019
Source ID
FA86501817811

Entities

People

  • Yaron Singer

Organizations

  • Air Force Research Laboratory
  • Defense Advanced Research Projects Agency
  • Harvard College

Tags

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks