Adversarial Sample Detection for Speaker Verification by Neural Vocoders

TL;DR

This paper proposes a neural vocoder-based method to detect adversarial samples in speaker verification systems, demonstrating superior performance over traditional baselines and dataset independence.

Contribution

It introduces a novel approach using neural vocoders for time-domain adversarial sample detection in speaker verification, with comprehensive experimental validation.

Findings

Outperforms Griffin-Lim baseline in detection accuracy

Effective across multiple datasets

Neural vocoder approach is dataset-independent

Abstract

Automatic speaker verification (ASV), one of the most important technology for biometric identification, has been widely adopted in security-critical applications. However, ASV is seriously vulnerable to recently emerged adversarial attacks, yet effective countermeasures against them are limited. In this paper, we adopt neural vocoders to spot adversarial samples for ASV. We use the neural vocoder to re-synthesize audio and find that the difference between the ASV scores for the original and re-synthesized audio is a good indicator for discrimination between genuine and adversarial samples. This effort is, to the best of our knowledge, among the first to pursue such a technical direction for detecting time-domain adversarial samples for ASV, and hence there is a lack of established baselines for comparison. Consequently, we implement the Griffin-Lim algorithm as the detection baseline. The proposed approach achieves effective detection performance that outperforms the baselines in all the settings. We also show that the neural vocoder adopted in the detection framework is dataset-independent. Our codes will be made open-source for future works to do fair comparison.