Home >

news Help

Publication Information


Title
Japanese: 
English:Quasi-Newton Adversarial Attacks on Speaker Verification Systems 
Author
Japanese: Goto Keita, 井上中順.  
English: Keita Goto, Nakamasa Inoue.  
Language English 
Journal/Book name
Japanese: 
English:2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) 
Volume, Number, Page         pp. 527-531
Published date Dec. 31, 2020 
Publisher
Japanese: 
English:IEEE 
Conference name
Japanese: 
English:Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2020（APSIPA ASC） 
Conference site
Japanese: 
English: 
Official URL http://www.apsipa.org/proceedings/2020/APSIPA-ASC-2020.html
 
Abstract This paper proposes a framework for generating adversarial utterances for speaker verification systems. Our main idea is to formulate an optimization problem to generate adversarial utterances that fool speaker verification models and solve it by a second-order optimization method. We first present our algorithm, which uses the first-order Gauss-Newton method, and then extend it to second-order Quasi-Newton methods. Our experiments on the VoxCeleb 1 dataset show that the proposed method can fool a speaker verification system with a smaller degree of perturbations than those of conventional methods. We also show that second-order optimization methods are effective for finding small perturbations.

©2007 Tokyo Institute of Technology All rights reserved.