Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples raises our concerns in adopting deep learning to safety-critical applications. As a result, we have witnessed increasing interests in s...

Full description

Saved in:
Bibliographic Details
Published in:International journal of automation and computing 2020-04, Vol.17 (2), p.151-178
Main Authors: Xu, Han, Ma, Yao, Liu, Hao-Chen, Deb, Debayan, Liu, Hui, Tang, Ji-Liang, Jain, Anil K.
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural networks
CAE) and Design
Cognitive tasks
Computer Applications
Computer-Aided Engineering (CAD
Control
Engineering
Graphs
Machine learning
Mechatronics
Review
Robotics
Safety critical
State-of-the-art reviews
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples raises our concerns in adopting deep learning to safety-critical applications. As a result, we have witnessed increasing interests in studying attack and defense mechanisms for DNN models on different data types, such as images, graphs and text. Thus, it is necessary to provide a systematic and comprehensive overview of the main threats of attacks and the success of corresponding countermeasures. In this survey, we review the state of the art algorithms for generating adversarial examples and the countermeasures against adversarial examples, for three most popular data types, including images, graphs and text.
ISSN:1476-8186
1751-8520
DOI:10.1007/s11633-019-1211-x