Universal Adversarial Perturbations Generative Network For Speaker Recognition

Abstract

Attacking deep learning based biometric systems has drawn more and more attention with the wide deployment of fingerprint/face/speaker recognition systems, given the fact that the neural networks are vulnerable to the adversarial examples, which have been intentionally perturbed to remain almost imperceptible for human. In this paper, we demonstrated the existence of the universal adversarial perturbations~(UAPs) for the speaker recognition systems. We proposed a generative network to learn the mapping from the low-dimensional normal distribution to the UAPs subspace, then synthesize the UAPs to perturbe any input signals to spoof the well-trained speaker recognition model with high probability. Experimental results on TIMIT and LibriSpeech datasets demonstrate the effectiveness of our model.

Stats

• citations43
• S2 citations—
• github stars0
• HF likes0
• heat score12.33
• arxiv keyli2020universal

Related papers

• Universal Adversarial Perturbations For Speech Recognition Systems (2019)14.11
• Inaudible Adversarial Perturbations For Targeted Attack In Speaker Recognition (2020)12.33
• Universal Adversarial Examples In Speech Command Classification (2019)0.00
• Adversarial Attack And Defense Strategies For Deep Speaker Recognition Systems (2020)13.39
• Adversarial Defense For Deep Speaker Recognition Using Hybrid Adversarial Training (2020)9.59
• Hiddenspeaker: Generate Imperceptible Unlearnable Audios For Speaker Verification System (2024)2.26
• Asynchronous Voice Anonymization Using Adversarial Perturbation On Speaker Embedding (2024)7.16
• Securing Voice Biometrics: One-shot Learning Approach For Audio Deepfake Detection (2023)9.03