Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systems

About

As the popularity of voice user interface (VUI) exploded in recent years, speaker recognition system has emerged as an important medium of identifying a speaker in many security-required applications and services. In this paper, we propose the first real-time, universal, and robust adversarial attack against the state-of-the-art deep neural network (DNN) based speaker recognition system. Through adding an audio-agnostic universal perturbation on arbitrary enrolled speaker's voice input, the DNN-based speaker recognition system would identify the speaker as any target (i.e., adversary-desired) speaker label. In addition, we improve the robustness of our attack by modeling the sound distortions caused by the physical over-the-air propagation through estimating room impulse response (RIR). Experiment using a public dataset of 109 English speakers demonstrates the effectiveness and robustness of our proposed attack with a high attack success rate of over 90%. The attack launching time also achieves a 100X speedup over contemporary non-universal attacks.

Yi Xie, Cong Shi, Zhuohang Li, Jian Liu, Yingying Chen, Bo Yuan• 2020

Related benchmarks

TaskDatasetResultRank
ASR AttackDeepSpeech2
SRoA-ASR6
5
Audio Imperceptibility EvaluationVCS (test)
SNR11.89
5
Speaker RecognitionSpeaker Recognition Dataset
ECAPA-TDNN Score0.734
5
ASR AttackWhisper
SRoA-ASR0.7
5
ASR AttackTencent ASR API
SRoA-ASR0.00e+0
5
ASR AttackAlibaba ASR API
SRoA-ASR0.00e+0
5
ASR AttackiFlytek ASR API
SRoA-ASR7.3
5
Showing 7 of 7 rows

Other info

Follow for update