Adversarial Deep Learning: A Survey on Adversarial Attacks and Defense Mechanisms on Image Classification
Open Access
- 20 September 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 102266-102291
Abstract
The popularity of adapting deep neural networks (DNNs) in solving hard problems has increased substantially. Specifically, in the field of computer vision, DNNs are becoming a core element in developing many image and video classification and recognition applications. However, DNNs are vulnerable to adversarial attacks, in which, given a well-trained image classification model, a malicious input can be crafted by adding mere perturbations to misclassify the image. This phenomena raise many security concerns in utilizing DNNs in critical life applications which attracts the attention of academic and industry researchers. As a result, multiple studies have proposed discussing novel attacks that can compromise the integrity of state-of-the-art image classification neural networks. The raise of these attacks urges the research community to explore countermeasure methods to mitigate these attacks and increase the reliability of adapting DDNs in different major applications. Hence, various defense strategies have been proposed to protect DNNs against adversarial attacks. In this paper, we thoroughly review the most recent and state-of-the-art adversarial attack methods by providing an in-depth analysis and explanation of the working process of these attacks. In our review, we focus on explaining the mathematical concepts and terminologies of the adversarial attacks, which provide a comprehensive and solid survey to the research community. Additionally, we provide a comprehensive review of the most recent defense mechanisms and discuss their effectiveness in defending DNNs against adversarial attacks. Finally, we highlight the current challenges and open issues in this field as well as future research directions.Keywords
This publication has 80 references indexed in Scilit:
- Vision for Looking at Traffic Lights: Issues, Survey, and PerspectivesIEEE Transactions on Intelligent Transportation Systems, 2016
- Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures2015
- Librispeech: An ASR corpus based on public domain audio books2015
- The human splicing code reveals new insights into the genetic determinants of diseaseScience, 2015
- Evasion Attacks against Machine Learning at Test Time2013
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse ProblemsSIAM Journal on Imaging Sciences, 2009
- Artificial Neural Networks2005
- Introduction to multi-layer feed-forward neural networksChemometrics and Intelligent Laboratory Systems, 1997
- Improving generalization performance using double backpropagationIEEE Transactions on Neural Networks, 1992
- A Stochastic Approximation MethodThe Annals of Mathematical Statistics, 1951