AudioFool: Fast, Universal and synchronization-free Cross-Domain Attack on Speech Recognition

TL;DR

This paper introduces AudioFool, a fast and universal adversarial attack method for speech recognition that is synchronization-free and effective over-the-air, enabling robust DoS attacks by manipulating audio in the frequency domain.

Contribution

The paper presents a novel attack generation technique that is robust to filtering and synchronization issues, specifically designed for over-the-air scenarios in speech recognition systems.

Findings

Effective in OTA conditions

Robust to filtering and synchronization issues

Achieves DoS attacks on ASR systems

Abstract

Automatic Speech Recognition systems have been shown to be vulnerable to adversarial attacks that manipulate the command executed on the device. Recent research has focused on exploring methods to create such attacks, however, some issues relating to Over-The-Air (OTA) attacks have not been properly addressed. In our work, we examine the needed properties of robust attacks compatible with the OTA model, and we design a method of generating attacks with arbitrary such desired properties, namely the invariance to synchronization, and the robustness to filtering: this allows a Denial-of-Service (DoS) attack against ASR systems. We achieve these characteristics by constructing attacks in a modified frequency domain through an inverse Fourier transform. We evaluate our method on standard keyword classification tasks and analyze it in OTA, and we analyze the properties of the cross-domain attacks to explain the efficiency of the approach.