2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Paper Detail

Paper IDIFS-3.6
Paper Title ATTACK ON PRACTICAL SPEAKER VERIFICATION SYSTEM USING UNIVERSAL ADVERSARIAL PERTURBATIONS
Authors Weiyi Zhang, Shuning Zhao, Tsinghua University, China; Le Liu, d-Ear Technologies, China; Jianmin Li, Xingliang Cheng, Thomas Fang Zheng, Xiaolin Hu, Tsinghua University, China
SessionIFS-3: Forensics and Biometrics
LocationGather.Town
Session Time:Wednesday, 09 June, 16:30 - 17:15
Presentation Time:Wednesday, 09 June, 16:30 - 17:15
Presentation Poster
Topic Information Forensics and Security: [MMH-OTHS] Forensics & Security Related Applications
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Virtual Presentation  Click here to watch in the Virtual Conference
Abstract In authentication scenarios, applications of practical speaker verification systems usually require a person to read a dynamic authentication text. Previous studies played an audio adversarial example as a digital signal to perform physical attacks, which would be easily rejected by audio replay detection modules. This work shows that by playing our crafted adversarial perturbation as a separate source when the adversary is speaking, the practical speaker verification system will misjudge the adversary as a target speaker. A two-step algorithm is proposed to optimize the universal adversarial perturbation to be text-independent and has little effect on the authentication text recognition. We also estimated room impulse response (RIR) in the algorithm which allowed the perturbation to be effective after being played over the air. In the physical experiment, we achieved targeted attacks with success rate of 100%, while the word error rate (WER) on speech recognition was only increased by 3.55%. And recorded audios could pass replay detection for the live person speaking.