A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learning

IEEE transactions on pattern analysis and machine intelligence, pp. 1-1, 2020.

Cited by: 0|Bibtex|Views16|DOI:https://doi.org/10.1109/TPAMI.2020.3032061
WOS
Other Links: arxiv.org|pubmed.ncbi.nlm.nih.gov|academic.microsoft.com

Abstract:

Although deep convolutional neural networks (CNNs) have demonstrated remarkable performance on multiple computer vision tasks, researches on adversarial learning have shown that deep models are vulnerable to adversarial examples. Most of the existing adversarial attack methods only create a single adversarial example for the input, which ...More

Code:

Data:

Your rating :
0

 

Tags
Comments