AdvSV: An Over-the-Air Adversarial Attack Dataset for Speaker Verification

TL;DR

This paper introduces AdvSV, an open-source dataset for over-the-air adversarial attacks on speaker verification systems, facilitating reproducible research and advancing robustness studies.

Contribution

The creation of a comprehensive, publicly available over-the-air adversarial attack dataset for speaker verification, addressing a key resource gap in the field.

Findings

Dataset includes adversarial samples recorded in real acoustic environments.

Baseline detection methods provided for reproducibility.

Dataset extends the scope of adversarial attack research in speaker verification.

Abstract

It is known that deep neural networks are vulnerable to adversarial attacks. Although Automatic Speaker Verification (ASV) built on top of deep neural networks exhibits robust performance in controlled scenarios, many studies confirm that ASV is vulnerable to adversarial attacks. The lack of a standard dataset is a bottleneck for further research, especially reproducible research. In this study, we developed an open-source adversarial attack dataset for speaker verification research. As an initial step, we focused on the over-the-air attack. An over-the-air adversarial attack involves a perturbation generation algorithm, a loudspeaker, a microphone, and an acoustic environment. The variations in the recording configurations make it very challenging to reproduce previous research. The AdvSV dataset is constructed using the Voxceleb1 Verification test set as its foundation. This dataset employs representative ASV models subjected to adversarial attacks and records adversarial samples to simulate over-the-air attack settings. The scope of the dataset can be easily extended to include more types of adversarial attacks. The dataset will be released to the public under the CC BY-SA 4.0. In addition, we also provide a detection baseline for reproducible research.