Generating Minimal Adversarial Perturbations with Integrated Adaptive Gradients

Deep neural networks are easily fooled high confidence predictions for adversarial samples

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Xiao, Yatie, Chi-Man Pun
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 20.05.2019
Subjects
Image classification
Neural networks
Pixels
Online AccessGet full text

Cover

More Information
Summary:Deep neural networks are easily fooled high confidence predictions for adversarial samples
ISSN:2331-8422