Adversarial attacks and robust defenses in deep learning

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 12 - Chapter in an edited book (Author)peer-review

4 Scopus Citations
View graph of relations

Author(s)

  • Jiang Liu
  • Wei-An Lin
  • Hossein Souri
  • Pirazh Khorramshahi
  • Rama Chellappa

Detail(s)

Original languageEnglish
Title of host publicationHandbook of Statistics
Subtitle of host publicationDeep Learning
EditorsVenu Govindaraju, Arni S.R. Srinivasa Rao, C.R. Rao
PublisherElsevier
Chapter3
Pages29-58
Number of pages30
Volume48
ISBN (print)978-0-443-18430-7
Publication statusPublished - 2023
Externally publishedYes

Publication series

NameHandbook of Statistics
Volume48
ISSN (Print)0169-7161

Abstract

Deep learning models have shown exceptional performance in many applications, including computer vision, natural language processing, and speech processing. However, if no defense strategy is considered, deep learning models are vulnerable to adversarial attacks. In this chapter, we will first describe various typical adversarial attacks. Then we will describe different adversarial defense methods for image classification and object detection tasks.

© 2023 Elsevier B.V. All rights reserved.

Research Area(s)

  • Adversarial attacks, Deep learning, Defenses against adversarial attacks

Bibliographic Note

Publisher Copyright: © 2023 Elsevier B.V.

Citation Format(s)

Adversarial attacks and robust defenses in deep learning. / Lau, Chun Pong; Liu, Jiang; Lin, Wei-An et al.
Handbook of Statistics: Deep Learning. ed. / Venu Govindaraju; Arni S.R. Srinivasa Rao; C.R. Rao. Vol. 48 Elsevier, 2023. p. 29-58 (Handbook of Statistics; Vol. 48).

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 12 - Chapter in an edited book (Author)peer-review