Open Access
ARTICLE
A Survey on Adversarial Examples in Deep Learning
Kai Chen1,*, Haoqi Zhu2, Leiming Yan1, Jinwei Wang1
1 School of Computer & Software, Nanjing University of Information Science & Technology, Nanjing, 210044, China
2 School of Atmospheric Sciences, Nanjing University of Information Science & Technology, Nanjing, 210044, China
* Corresponding Author: Kai Chen. Email:
Journal on Big Data 2020, 2(2), 71-84. https://doi.org/10.32604/jbd.2020.012294
Received 15 March 2020; Accepted 15 July 2020; Issue published 18 September 2020
Abstract
Adversarial examples are hot topics in the field of security in deep
learning. The feature, generation methods, attack and defense methods of the
adversarial examples are focuses of the current research on adversarial examples.
This article explains the key technologies and theories of adversarial examples
from the concept of adversarial examples, the occurrences of the adversarial
examples, the attacking methods of adversarial examples. This article lists the
possible reasons for the adversarial examples. This article also analyzes several
typical generation methods of adversarial examples in detail: Limited-memory
BFGS (L-BFGS), Fast Gradient Sign Method (FGSM), Basic Iterative Method
(BIM), Iterative Least-likely Class Method (LLC), etc. Furthermore, in the
perspective of the attack methods and reasons of the adversarial examples, the
main defense techniques for the adversarial examples are listed: preprocessing,
regularization and adversarial training method, distillation method, etc., which
application scenarios and deficiencies of different defense measures are pointed
out. This article further discusses the application of adversarial examples which
currently is mainly used in adversarial evaluation and adversarial training.
Finally, the overall research direction of the adversarial examples is prospected
to completely solve the adversarial attack problem. There are still a lot of
practical and theoretical problems that need to be solved. Finding out the
characteristics of the adversarial examples, giving a mathematical description of
its practical application prospects, exploring the universal method of adversarial
example generation and the generation mechanism of the adversarial examples
are the main research directions of the adversarial examples in the future.
Keywords
Cite This Article
K. Chen, H. Zhu, L. Yan and J. Wang, "A survey on adversarial examples in deep learning,"
Journal on Big Data, vol. 2, no.2, pp. 71–84, 2020. https://doi.org/10.32604/jbd.2020.012294
Citations