Simultaneous Attack on CNN-Based Monocular Depth Estimation and Optical Flow Estimation

Koichiro YAMANAKA; Keita TAKAHASHI; Toshiaki FUJII; Ryuraroh MATSUMOTO

doi:10.1587/transinf.2021EDL8004

Simultaneous Attack on CNN-Based Monocular Depth Estimation and Optical Flow Estimation

Koichiro YAMANAKA, Keita TAKAHASHI, Toshiaki FUJII, Ryuraroh MATSUMOTO

Full Text Views

0

Cite this

Summary :

Thanks to the excellent learning capability of deep convolutional neural networks (CNNs), CNN-based methods have achieved great success in computer vision and image recognition tasks. However, it has turned out that these methods often have inherent vulnerabilities, which makes us cautious of the potential risks of using them for real-world applications such as autonomous driving. To reveal such vulnerabilities, we propose a method of simultaneously attacking monocular depth estimation and optical flow estimation, both of which are common artificial-intelligence-based tasks that are intensively investigated for autonomous driving scenarios. Our method can generate an adversarial patch that can fool CNN-based monocular depth estimation and optical flow estimation methods simultaneously by simply placing the patch in the input images. To the best of our knowledge, this is the first work to achieve simultaneous patch attacks on two or more CNNs developed for different tasks.

Publication: IEICE TRANSACTIONS on Information Vol.E104-D No.5 pp.785-788

Publication Date: 2021/05/01

Publicized: 2021/02/08

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2021EDL8004

Type of Manuscript: LETTER

Category: Image Recognition, Computer Vision

Authors

Koichiro YAMANAKA
  Nagoya University
Keita TAKAHASHI
  Nagoya University
Toshiaki FUJII
  Nagoya University
Ryuraroh MATSUMOTO
  Tokyo Institute of Technology

Keyword

adversarial attack, monocular depth estimation, optical flow estimation, CNN

Cite this

Copy

Koichiro YAMANAKA, Keita TAKAHASHI, Toshiaki FUJII, Ryuraroh MATSUMOTO, "Simultaneous Attack on CNN-Based Monocular Depth Estimation and Optical Flow Estimation" in IEICE TRANSACTIONS on Information, vol. E104-D, no. 5, pp. 785-788, May 2021, doi: 10.1587/transinf.2021EDL8004.
Abstract: Thanks to the excellent learning capability of deep convolutional neural networks (CNNs), CNN-based methods have achieved great success in computer vision and image recognition tasks. However, it has turned out that these methods often have inherent vulnerabilities, which makes us cautious of the potential risks of using them for real-world applications such as autonomous driving. To reveal such vulnerabilities, we propose a method of simultaneously attacking monocular depth estimation and optical flow estimation, both of which are common artificial-intelligence-based tasks that are intensively investigated for autonomous driving scenarios. Our method can generate an adversarial patch that can fool CNN-based monocular depth estimation and optical flow estimation methods simultaneously by simply placing the patch in the input images. To the best of our knowledge, this is the first work to achieve simultaneous patch attacks on two or more CNNs developed for different tasks.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDL8004/_p

Copy

@ARTICLE{e104-d_5_785,
author={Koichiro YAMANAKA, Keita TAKAHASHI, Toshiaki FUJII, Ryuraroh MATSUMOTO, },
journal={IEICE TRANSACTIONS on Information},
title={Simultaneous Attack on CNN-Based Monocular Depth Estimation and Optical Flow Estimation},
year={2021},
volume={E104-D},
number={5},
pages={785-788},
abstract={Thanks to the excellent learning capability of deep convolutional neural networks (CNNs), CNN-based methods have achieved great success in computer vision and image recognition tasks. However, it has turned out that these methods often have inherent vulnerabilities, which makes us cautious of the potential risks of using them for real-world applications such as autonomous driving. To reveal such vulnerabilities, we propose a method of simultaneously attacking monocular depth estimation and optical flow estimation, both of which are common artificial-intelligence-based tasks that are intensively investigated for autonomous driving scenarios. Our method can generate an adversarial patch that can fool CNN-based monocular depth estimation and optical flow estimation methods simultaneously by simply placing the patch in the input images. To the best of our knowledge, this is the first work to achieve simultaneous patch attacks on two or more CNNs developed for different tasks.},
keywords={},
doi={10.1587/transinf.2021EDL8004},
ISSN={1745-1361},
month={May},}

Copy

TY - JOUR
TI - Simultaneous Attack on CNN-Based Monocular Depth Estimation and Optical Flow Estimation
T2 - IEICE TRANSACTIONS on Information
SP - 785
EP - 788
AU - Koichiro YAMANAKA
AU - Keita TAKAHASHI
AU - Toshiaki FUJII
AU - Ryuraroh MATSUMOTO
PY - 2021
DO - 10.1587/transinf.2021EDL8004
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2021
AB - Thanks to the excellent learning capability of deep convolutional neural networks (CNNs), CNN-based methods have achieved great success in computer vision and image recognition tasks. However, it has turned out that these methods often have inherent vulnerabilities, which makes us cautious of the potential risks of using them for real-world applications such as autonomous driving. To reveal such vulnerabilities, we propose a method of simultaneously attacking monocular depth estimation and optical flow estimation, both of which are common artificial-intelligence-based tasks that are intensively investigated for autonomous driving scenarios. Our method can generate an adversarial patch that can fool CNN-based monocular depth estimation and optical flow estimation methods simultaneously by simply placing the patch in the input images. To the best of our knowledge, this is the first work to achieve simultaneous patch attacks on two or more CNNs developed for different tasks.
ER -