Skip to content

Ian-Tam/Papers-on-Speech-System-Adversarial-Attack-and-Defense

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

47 Commits
 
 

Repository files navigation

- Introduction

分类存放语音技术、对抗算法和防御的文章(文章,代码,简介,链接,会议/期刊,年份),目前主要包括语音识别和声纹识别两大领域的论文。


- Speech Recognition

【1】Survey

【2】Attack Papers

  1. CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition [paper] [video] [code] [method] USENIX2018

方法简介:在歌曲中嵌入指令。对kaldi里的“ASpIRE Chain Model” 攻击,模型是HMM-DNN,指定command,载体声音向command的token序列定向移动。

  1. ###隐藏语音命令[[paper](https://security.cs.georgetown.edu/~tavish/hvc_usenix.pdf)] [[video] (https://www.usenix.org/conference/ usenixsecurity16 / technical-sessions / presentation / carlini)] USENIX2016
    remain to be introduced

【3】Defense Papers

【4】Related Techniques


- Speaker Recognition/Verfication

【1】Survey

【2】Attack Papers

1、Learning to fool the speaker recognition. [Jiguo Li, ..] (papercodeWeb) ICASSP 2020

【3】Defense Papers

【4】Related Techniques

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published