Evaluating robustness of deep image super-resolution against adversarial attacks

Jun Ho Choi; Huan Zhang; Jun Hyuk Kim; Cho Jui Hsieh; Jong Seok Lee

doi:10.1109/ICCV.2019.00039

Evaluating robustness of deep image super-resolution against adversarial attacks

Jun Ho Choi, Huan Zhang, Jun Hyuk Kim, Cho Jui Hsieh, Jong Seok Lee

School of Integrated Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

56 Citations (Scopus)

Abstract

Single-image super-resolution aims to generate a high-resolution version of a low-resolution image, which serves as an essential component in many image processing applications. This paper investigates the robustness of deep learning-based super-resolution methods against adversarial attacks, which can significantly deteriorate the super-resolved images without noticeable distortion in the attacked low-resolution images. It is demonstrated that state-of-the-art deep super-resolution methods are highly vulnerable to adversarial attacks. Different levels of robustness of different methods are analyzed theoretically and experimentally. We also present analysis on transferability of attacks, and feasibility of targeted attacks and universal attacks.

Original language	English
Title of host publication	Proceedings - 2019 International Conference on Computer Vision, ICCV 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	303-311
Number of pages	9
ISBN (Electronic)	9781728148038
DOIs	https://doi.org/10.1109/ICCV.2019.00039
Publication status	Published - 2019 Oct
Event	17th IEEE/CVF International Conference on Computer Vision, ICCV 2019 - Seoul, Korea, Republic of Duration: 2019 Oct 27 → 2019 Nov 2

Publication series

Name	Proceedings of the IEEE International Conference on Computer Vision
ISSN (Print)	1550-5499

Conference

Conference	17th IEEE/CVF International Conference on Computer Vision, ICCV 2019
Country/Territory	Korea, Republic of
City	Seoul
Period	19/10/27 → 19/11/2

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

All Science Journal Classification (ASJC) codes

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/ICCV.2019.00039

Cite this

Choi, J. H., Zhang, H., Kim, J. H., Hsieh, C. J., & Lee, J. S. (2019). Evaluating robustness of deep image super-resolution against adversarial attacks. In Proceedings - 2019 International Conference on Computer Vision, ICCV 2019 (pp. 303-311). Article 9010873 (Proceedings of the IEEE International Conference on Computer Vision). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2019.00039

@inproceedings{79dc7ad3455144e6809a6d7ce114f655,

title = "Evaluating robustness of deep image super-resolution against adversarial attacks",

abstract = "Single-image super-resolution aims to generate a high-resolution version of a low-resolution image, which serves as an essential component in many image processing applications. This paper investigates the robustness of deep learning-based super-resolution methods against adversarial attacks, which can significantly deteriorate the super-resolved images without noticeable distortion in the attacked low-resolution images. It is demonstrated that state-of-the-art deep super-resolution methods are highly vulnerable to adversarial attacks. Different levels of robustness of different methods are analyzed theoretically and experimentally. We also present analysis on transferability of attacks, and feasibility of targeted attacks and universal attacks.",

author = "Choi, {Jun Ho} and Huan Zhang and Kim, {Jun Hyuk} and Hsieh, {Cho Jui} and Lee, {Jong Seok}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 17th IEEE/CVF International Conference on Computer Vision, ICCV 2019 ; Conference date: 27-10-2019 Through 02-11-2019",

year = "2019",

month = oct,

doi = "10.1109/ICCV.2019.00039",

language = "English",

series = "Proceedings of the IEEE International Conference on Computer Vision",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "303--311",

booktitle = "Proceedings - 2019 International Conference on Computer Vision, ICCV 2019",

address = "United States",

}

Choi, JH, Zhang, H, Kim, JH, Hsieh, CJ & Lee, JS 2019, Evaluating robustness of deep image super-resolution against adversarial attacks. in Proceedings - 2019 International Conference on Computer Vision, ICCV 2019., 9010873, Proceedings of the IEEE International Conference on Computer Vision, Institute of Electrical and Electronics Engineers Inc., pp. 303-311, 17th IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea, Republic of, 19/10/27. https://doi.org/10.1109/ICCV.2019.00039

Evaluating robustness of deep image super-resolution against adversarial attacks. / Choi, Jun Ho; Zhang, Huan; Kim, Jun Hyuk et al.
Proceedings - 2019 International Conference on Computer Vision, ICCV 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 303-311 9010873 (Proceedings of the IEEE International Conference on Computer Vision).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Evaluating robustness of deep image super-resolution against adversarial attacks

AU - Choi, Jun Ho

AU - Zhang, Huan

AU - Kim, Jun Hyuk

AU - Hsieh, Cho Jui

AU - Lee, Jong Seok

PY - 2019/10

Y1 - 2019/10

N2 - Single-image super-resolution aims to generate a high-resolution version of a low-resolution image, which serves as an essential component in many image processing applications. This paper investigates the robustness of deep learning-based super-resolution methods against adversarial attacks, which can significantly deteriorate the super-resolved images without noticeable distortion in the attacked low-resolution images. It is demonstrated that state-of-the-art deep super-resolution methods are highly vulnerable to adversarial attacks. Different levels of robustness of different methods are analyzed theoretically and experimentally. We also present analysis on transferability of attacks, and feasibility of targeted attacks and universal attacks.

AB - Single-image super-resolution aims to generate a high-resolution version of a low-resolution image, which serves as an essential component in many image processing applications. This paper investigates the robustness of deep learning-based super-resolution methods against adversarial attacks, which can significantly deteriorate the super-resolved images without noticeable distortion in the attacked low-resolution images. It is demonstrated that state-of-the-art deep super-resolution methods are highly vulnerable to adversarial attacks. Different levels of robustness of different methods are analyzed theoretically and experimentally. We also present analysis on transferability of attacks, and feasibility of targeted attacks and universal attacks.

UR - http://www.scopus.com/inward/record.url?scp=85081886069&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85081886069&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2019.00039

DO - 10.1109/ICCV.2019.00039

M3 - Conference contribution

AN - SCOPUS:85081886069

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 303

EP - 311

BT - Proceedings - 2019 International Conference on Computer Vision, ICCV 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th IEEE/CVF International Conference on Computer Vision, ICCV 2019

Y2 - 27 October 2019 through 2 November 2019

ER -

Choi JH, Zhang H, Kim JH, Hsieh CJ, Lee JS. Evaluating robustness of deep image super-resolution against adversarial attacks. In Proceedings - 2019 International Conference on Computer Vision, ICCV 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 303-311. 9010873. (Proceedings of the IEEE International Conference on Computer Vision). doi: 10.1109/ICCV.2019.00039

Evaluating robustness of deep image super-resolution against adversarial attacks

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this