ITE Technical Group Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2019-12-06 10:10
Adversarial Examples for Monocular Depth Estimation CNN
Koichiro Yamanaka, Ryutaroh Matsumoto, Keita Takahashi, Toshiaki Fujii (Nagoya Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) Adversarial examples for classification and object recognition problems using convolutional neural net- works (CNN) have attracted much attention in recent years. By adding perturbations to an input image of a CNN, adversarial attack is able to intentionally induce erroneous inferences. Adversarial attack is roughly classified into two types. The one is a method that slightly changes the pixel values of an entire input image, and the other is a method that overwrites a specific pattern (adversarial patch) on a local region of the input image. The latter method is called the adversarial patch attack, and recently real world attack was proposed by using this method. In other words, the classification CNN and the object recognition CNN could be deceived by taking a printed adversarial patch with a camera. However, adversarial attacks on regression problems have not been studied well. In this paper, we propose an adversarial attack method for regression problem, especially for monocular depth estimation CNN. We demonstrate that our method is capable of generating adversarial patches that can arbitrarily manipulate the output of the monocular depth estimation.
Keyword (in Japanese) (See Japanese page) 
(in English) Monocular Depth Estimation / CNN / Adversarial Examples / Adversarial Patch / / / /  
Reference Info. ITE Tech. Rep.
Paper #  
Date of Issue  
ISSN Print edition: ISSN 1342-6893  Online edition: ISSN 2424-1970
Download PDF

Conference Information
Conference Date 2019-12-05 - 2019-12-06 
Place (in Japanese) (See Japanese page) 
Place (in English) Aiina Center 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Image coding, Communications and streaming technologies, etc. 
Paper Information
Registration To IEICE-CS 
Conference Code 2019-12-IE-CS-AVM-BCT 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Adversarial Examples for Monocular Depth Estimation CNN 
Sub Title (in English)  
Keyword(1) Monocular Depth Estimation  
Keyword(2) CNN  
Keyword(3) Adversarial Examples  
Keyword(4) Adversarial Patch  
1st Author's Name Koichiro Yamanaka  
1st Author's Affiliation Nagoya University (Nagoya Univ.)
2nd Author's Name Ryutaroh Matsumoto  
2nd Author's Affiliation Nagoya University (Nagoya Univ.)
3rd Author's Name Keita Takahashi  
3rd Author's Affiliation Nagoya University (Nagoya Univ.)
4th Author's Name Toshiaki Fujii  
4th Author's Affiliation Nagoya University (Nagoya Univ.)
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Date Time 2019-12-06 10:10:00 
Presentation Time 25 
Registration for IEICE-CS 
Paper #  
Volume (vol) 43 
Number (no)  
Date of Issue  

[Return to Top Page]

[Return to ITE Web Page]

The Institute of Image Information and Television Engineers (ITE), Japan