Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
2 files | 7.05 MB
Add to list
  1. Search results
  2. An introduction to adversarially robu...

An introduction to adversarially robust deep learning

Jonathan Peck (UGent) , Bart Goossens (UGent) and Yvan Saeys (UGent)
(2024) IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. 46(4). p.2071-2090
Author
Organization
Project
Abstract
The widespread success of deep learning in solving machine learning problems has fueled its adoption in many fields, from speech recognition to drug discovery and medical imaging. However, deep learning systems are extremely fragile: imperceptibly small modifications to their input data can cause the models to produce erroneous output. It is very easy to generate such adversarial perturbations even for state-of-the-art models, yet immunization against them has proven exceptionally challenging. Despite over a decade of research on this problem, our solutions are still far from satisfactory and many open problems remain. In this work, we survey some of the most important contributions in the fi eld of adversarial robustness. We pay particular attention to the reasons why past attempts at improving robustness have been insuffi cient, and we identify several promising areas for future research.
Keywords
Applied Mathematics, Artificial Intelligence, Computational Theory and Mathematics, Computer Vision and Pattern Recognition, Software, deep learning, computer vision, Adversarial machine learning

Downloads

  • Download
    Survey TPAMI 2023 preprint.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 4.08 MB
  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 2.97 MB

Citation

Please use this url to cite or link to this publication:

MLA
Peck, Jonathan, et al. “An Introduction to Adversarially Robust Deep Learning.” IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol. 46, no. 4, 2024, pp. 2071–90, doi:10.1109/tpami.2023.3331087.
APA
Peck, J., Goossens, B., & Saeys, Y. (2024). An introduction to adversarially robust deep learning. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 46(4), 2071–2090. https://doi.org/10.1109/tpami.2023.3331087
Chicago author-date
Peck, Jonathan, Bart Goossens, and Yvan Saeys. 2024. “An Introduction to Adversarially Robust Deep Learning.” IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 46 (4): 2071–90. https://doi.org/10.1109/tpami.2023.3331087.
Chicago author-date (all authors)
Peck, Jonathan, Bart Goossens, and Yvan Saeys. 2024. “An Introduction to Adversarially Robust Deep Learning.” IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 46 (4): 2071–2090. doi:10.1109/tpami.2023.3331087.
Vancouver
1.
Peck J, Goossens B, Saeys Y. An introduction to adversarially robust deep learning. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. 2024;46(4):2071–90.
IEEE
[1]
J. Peck, B. Goossens, and Y. Saeys, “An introduction to adversarially robust deep learning,” IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol. 46, no. 4, pp. 2071–2090, 2024.
@article{01HFV843F8DG5FJ6CMNREX9DWB,
  abstract     = {{The widespread success of deep learning in solving machine learning problems has fueled its adoption in many fields, from speech recognition to drug discovery and medical imaging. However, deep learning systems are extremely fragile: imperceptibly small modifications to their input data can cause the models to produce erroneous output. It is very easy to generate such adversarial perturbations even for state-of-the-art models, yet immunization against them has proven exceptionally challenging. Despite over a decade of research on this problem, our solutions are still far from satisfactory and many open problems remain. In this work, we survey some of the most important contributions in the fi eld of adversarial robustness. We pay particular attention to the reasons why past attempts at improving robustness have been insuffi cient, and we identify several promising areas for future research.}},
  author       = {{Peck, Jonathan and Goossens, Bart and Saeys, Yvan}},
  issn         = {{0162-8828}},
  journal      = {{IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE}},
  keywords     = {{Applied Mathematics,Artificial Intelligence,Computational Theory and Mathematics,Computer Vision and Pattern Recognition,Software,deep learning,computer vision,Adversarial machine learning}},
  language     = {{eng}},
  number       = {{4}},
  pages        = {{2071--2090}},
  title        = {{An introduction to adversarially robust deep learning}},
  url          = {{http://doi.org/10.1109/tpami.2023.3331087}},
  volume       = {{46}},
  year         = {{2024}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: