Studies Advanced in Image Recognition based on Adversarial Learning

DOI

10.2991/978-94-6463-300-9_97How to use a DOI?

Keywords

Image recognition; Adversarial learning; Deep learning

Abstract

In recent years, adversarial learning has gradually attracted a lot of research interest, which aims to understand the attack behavior and design various algorithms that can resist the attack. The design of adversarial learning algorithms mostly revolves around the generation of adversarial examples, which refer to samples that are carefully crafted for these recognition tasks to confuse and mislead detection tasks. Adversarial learning finds applications in various domains including medical care, finance, security, and autonomous driving, demonstrating promising prospects. Taking the classical image recognition task as an example, this paper provides a detailed overview of recent developments in adversarial learning. Specifically, two main frameworks and corresponding representative algorithms of adversarial learning are introduced, including their design ideas, key steps, advantages, and disadvantages. Then, quantitative results of different classification algorithms on common datasets are analyzed and compared. The article concludes by summarizing the difficulties in balancing accuracy and robustness, parameter settings, algorithm selection, and prospects for the future development of adversarial learning, which can provide some new insights for the research field of adversarial learning.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Jiaqi Liao
PY  - 2023
DA  - 2023/11/27
TI  - Studies Advanced in Image Recognition based on Adversarial Learning
BT  - Proceedings of the 2023 International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2023)
PB  - Atlantis Press
SP  - 961
EP  - 970
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-300-9_97
DO  - 10.2991/978-94-6463-300-9_97
ID  - Liao2023
ER  -