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 2021-10-07 14:25
Block-wise Transformation with Secret Key for Adversary Robust Defence of SVM model
Ryota Iijima, MaungMaung AprilPyone, Hitoshi Kiya (TMU)
Abstract (in Japanese) (See Japanese page) 
(in English) In this paper, we propose a method for implementing support vector machine (SVM) models that are robust against adversarial examples, in which a transformation method using a secret key is applied to training and test images. Block-wise transformation methods with a secret key have been developed for adversarially robust defense, but their applications are limited to deep neural network (DNN) models Accordingly, in this paper, the conventional transformations are demonstrated to be ineffective for SVM models, so we propose a novel transformation method with a key for SVM models.In a face image classification experiment, the proposed transformation is verified to be effective in constructing adversarially robust SVM models against adversarial examples.
Keyword (in Japanese) (See Japanese page) 
(in English) Support Vector Machine / Adversarial Examples / Image Transformation / / / / /  
Reference Info. ITE Tech. Rep.
Paper #  
Date of Issue  
ISSN  
Download PDF

Conference Information
Committee BCT IEICE-SIS  
Conference Date 2021-10-07 - 2021-10-08 
Place (in Japanese) (See Japanese page) 
Place (in English) online 
Topics (in Japanese) (See Japanese page) 
Topics (in English) System Implementation Technology, Short Range Wireless Systems, Smart Multimedia Systems, Broadcasting Technology, etc. 
Paper Information
Registration To IEICE-SIS 
Conference Code 2021-10-SIS-BCT 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Block-wise Transformation with Secret Key for Adversary Robust Defence of SVM model 
Sub Title (in English)  
Keyword(1) Support Vector Machine  
Keyword(2) Adversarial Examples  
Keyword(3) Image Transformation  
Keyword(4)  
Keyword(5)  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Ryota Iijima  
1st Author's Affiliation Tokyo Metropolitan University (TMU)
2nd Author's Name MaungMaung AprilPyone  
2nd Author's Affiliation Tokyo Metropolitan University (TMU)
3rd Author's Name Hitoshi Kiya  
3rd Author's Affiliation Tokyo Metropolitan University (TMU)
4th Author's Name  
4th Author's Affiliation ()
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 ()
Speaker Author-1 
Date Time 2021-10-07 14:25:00 
Presentation Time 20 minutes 
Registration for IEICE-SIS 
Paper #  
Volume (vol) vol.45 
Number (no)  
Page  
#Pages  
Date of Issue  


[Return to Top Page]

[Return to ITE Web Page]


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