LMD: A Learnable Mask Network to Detect Adversarial Examples for Speaker Verification

by   Xing Chen, et al.

Although the security of automatic speaker verification (ASV) is seriously threatened by recently emerged adversarial attacks, there have been some countermeasures to alleviate the threat. However, many defense approaches not only require the prior knowledge of the attackers but also possess weak interpretability. To address this issue, in this paper, we propose an attacker-independent and interpretable method, named learnable mask detector (LMD), to separate adversarial examples from the genuine ones. It utilizes score variation as an indicator to detect adversarial examples, where the score variation is the absolute discrepancy between the ASV scores of an original audio recording and its transformed audio synthesized from its masked complex spectrogram. A core component of the score variation detector is to generate the masked spectrogram by a neural network. The neural network needs only genuine examples for training, which makes it an attacker-independent approach. Its interpretability lies that the neural network is trained to minimize the score variation of the targeted ASV, and maximize the number of the masked spectrogram bins of the genuine training examples. Its foundation is based on the observation that, masking out the vast majority of the spectrogram bins with little speaker information will inevitably introduce a large score variation to the adversarial example, and a small score variation to the genuine example. Experimental results with 12 attackers and two representative ASV systems show that our proposed method outperforms five state-of-the-art baselines. The extensive experimental results can also be a benchmark for the detection-based ASV defenses.


page 1

page 11


Stochastic Substitute Training: A Gray-box Approach to Craft Adversarial Examples Against Gradient Obfuscation Defenses

It has been shown that adversaries can craft example inputs to neural ne...

Fooling End-to-end Speaker Verification by Adversarial Examples

Automatic speaker verification systems are increasingly used as the prim...

Robust Audio Adversarial Example for a Physical Attack

The success of deep learning in recent years has raised concerns about a...

On the Detection of Adaptive Adversarial Attacks in Speaker Verification Systems

Speaker verification systems have been widely used in smart phones and I...

Push-Pull: Characterizing the Adversarial Robustness for Audio-Visual Active Speaker Detection

Audio-visual active speaker detection (AVASD) is well-developed, and now...

Adversarial Examples Detection and Analysis with Layer-wise Autoencoders

We present a mechanism for detecting adversarial examples based on data ...

Voting for the right answer: Adversarial defense for speaker verification

Automatic speaker verification (ASV) is a well developed technology for ...

Please sign up or login with your details

Forgot password? Click here to reset