Making Machine Learning Robust Against Adversarial Inputs.

The article discusses the failure of machine learning algorithms that exceed human performance in naturally occurring scenarios when an adversary is able to modify their input data. Topics include the use of model training, input validation and architectural changes to defend against adversaries, an...

Full description

Bibliographic Details

Published in:	Communications of the ACM Vol. 61; no. 7; pp. 56 - 67
Main Authors:	GOODFELLOW, IAN, MCDANIEL, PATRICK, PAPERNOT, NICOLAS
Format:	Article
Published:	Association for Computing Machinery Jul2018
Subjects:	Machine learning Algorithms Computer input design Computer programming Computer security Security systems
Online Access:	View this record in EBSCOhost