Over-the-air White-box Attack on the Wav2Vec Speech Recognition Neural Network

Abstract

Automatic speech recognition systems based on neural networks are vulnerable to adversarial attacks that alter transcriptions in a malicious way. Recent works in this field have focused on making attacks work in over-the-air scenarios, however such attacks are typically detectable by human hearing, limiting their potential applications. In the present work we explore different approaches of making over-the-air attacks less detectable, as well as the impact these approaches have on the attacks' effectiveness.

Figures (5)

• Figure 1: Data augmentation.
• Figure 2: Example room layout.
• Figure 3: Attack generation iteration. Gradient backpropagation is indicated by red arrows.
• Figure 4: Audio fragments padded with zeros.
• Figure 5: Numbers of iterations required to reach various values of $\lambda$.