Adversarial defense for automatic speaker verification by cascaded self-supervised learning models

Abstract

Automatic speaker verification (ASV) is one of the core technologies in biometric identification. With the ubiquitous usage of ASV systems in safety-critical applications, more and more malicious attackers attempt to launch adversarial attacks at ASV systems. In the midst of the arms race between attack and defense in ASV, how to effectively improve the robustness of ASV against adversarial attacks remains an open question. We note that the self-supervised learning models possess the ability to mitigate superficial perturbations in the input after pretraining. Hence, with the goal of effective defense in ASV against adversarial attacks, we propose a standard and attack-agnostic method based on cascaded self-supervised learning models to purify the adversarial perturbations. Experimental results demonstrate that the proposed method achieves effective defense performance and can successfully counter adversarial attacks in scenarios where attackers may either be aware or unaware of the self-supervised learning models.

Accepted to ICASSP 2021

References in corpus (6)

• BUT System Description to VoxCeleb Speaker Recognition Challenge 2019
• The Attacker's Perspective on Automatic Speaker Verification: An Overview
• Adversarial Attacks on Spoofing Countermeasures of automatic speaker verification
• Inaudible Adversarial Perturbations for Targeted Attack in Speaker Recognition
• Investigating Robustness of Adversarial Samples Detection for Automatic Speaker Verification
• Bayesian x-vector: Bayesian Neural Network based x-vector System for Speaker Verification