Opportunistic Backdoor Attacks: Exploring Human-imperceptible Vulnerabilities on Speech Recognition Systems

Author:

Liu Qiang1,Zhou Tongqing1,Cai Zhiping1,Tang Yonghao1

Affiliation:

1. National University of Defense Technology, Changsha, China

Funder

National Key Research and Development Program of China

Natural Science Foundation of Hunan Province

Science and Technology Innovation Program of Hunan Province

National Natural Science Foundation of China

Publisher

ACM

Reference33 articles.

1. Hojjat Aghakhani , Lea Schönherr , Thorsten Eisenhofer , Dorothea Kolossa , Thorsten Holz , Christopher Kruegel , and Giovanni Vigna . 2020. VenoMave: Targeted Poisoning Against Speech Recognition. arXiv preprint arXiv:2010.10682 ( 2020 ). Hojjat Aghakhani, Lea Schönherr, Thorsten Eisenhofer, Dorothea Kolossa, Thorsten Holz, Christopher Kruegel, and Giovanni Vigna. 2020. VenoMave: Targeted Poisoning Against Speech Recognition. arXiv preprint arXiv:2010.10682 (2020).

2. Image method for efficiently simulating small‐room acoustics

3. Nicholas Carlini , Pratyush Mishra , Tavish Vaidya , Yuankai Zhang , Micah Sherr , Clay Shields , David Wagner , and Wenchao Zhou . 2016 . Hidden voice commands . In Proc. of USENIX Security Symposium. 513--530 . Nicholas Carlini, Pratyush Mishra, Tavish Vaidya, Yuankai Zhang, Micah Sherr, Clay Shields, David Wagner, and Wenchao Zhou. 2016. Hidden voice commands. In Proc. of USENIX Security Symposium. 513--530.

4. Audio Adversarial Examples: Targeted Attacks on Speech-to-Text

5. Xinyun Chen , Chang Liu , Bo Li , Kimberly Lu , and Dawn Song . 2017. Targeted backdoor attacks on deep learning systems using data poisoning. arXiv preprint arXiv:1712.05526 ( 2017 ). Xinyun Chen, Chang Liu, Bo Li, Kimberly Lu, and Dawn Song. 2017. Targeted backdoor attacks on deep learning systems using data poisoning. arXiv preprint arXiv:1712.05526 (2017).

Cited by 9 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Audio Steganography Based Backdoor Attack for Speech Recognition Software;2024 IEEE 48th Annual Computers, Software, and Applications Conference (COMPSAC);2024-07-02

2. SpeechGuard: Online Defense against Backdoor Attacks on Speech Recognition Models;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

3. FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledge;2024 IEEE Symposium on Security and Privacy (SP);2024-05-19

4. Breaking Speaker Recognition with Paddingback;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

5. Toward Stealthy Backdoor Attacks Against Speech Recognition via Elements of Sound;IEEE Transactions on Information Forensics and Security;2024

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3