Characterizing Audio Adversarial Examples Using Temporal Dependency

by   Zhuolin Yang, et al.

Recent studies have highlighted adversarial examples as a ubiquitous threat to different neural network models and many downstream applications. Nonetheless, as unique data properties have inspired distinct and powerful learning principles, this paper aims to explore their potentials towards mitigating adversarial inputs. In particular, our results reveal the importance of using the temporal dependency in audio data to gain discriminate power against adversarial examples. Tested on the automatic speech recognition (ASR) tasks and three recent audio adversarial attacks, we find that (i) input transformation developed from image adversarial defense provides limited robustness improvement and is subtle to advanced attacks; (ii) temporal dependency can be exploited to gain discriminative power against audio adversarial examples and is resistant to adaptive attacks considered in our experiments. Our results not only show promising means of improving the robustness of ASR systems, but also offer novel insights in exploiting domain-specific data properties to mitigate negative effects of adversarial examples.


page 6

page 13


WaveGuard: Understanding and Mitigating Audio Adversarial Examples

There has been a recent surge in adversarial attacks on deep learning ba...

Adversarial attack on Speech-to-Text Recognition Models

Recent studies have highlighted audio adversarial examples as a ubiquito...

A Multiversion Programming Inspired Approach to Detecting Audio Adversarial Examples

Adversarial examples (AEs) are crafted by adding human-imperceptible per...

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

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

Towards the Universal Defense for Query-Based Audio Adversarial Attacks

Recently, studies show that deep learning-based automatic speech recogni...

Dompteur: Taming Audio Adversarial Examples

Adversarial examples seem to be inevitable. These specifically crafted i...

Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement

Recent studies have highlighted adversarial examples as ubiquitous threa...

Please sign up or login with your details

Forgot password? Click here to reset