# Detecting Audio Attacks on ASR Systems with Dropout Uncertainty

arXiv: https://arxiv.org/abs/2006.01906 · HTML: https://mlsanity.com/paper/2006.01906/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jun 2020.

## Built on by (most cited first, 1 of 1)

- [MIXPGD: Hybrid Adversarial Training for Speech Recognition Systems](https://mlsanity.com/paper/2303.05758/) (2023)

## Abstract (arXiv)

Various adversarial audio attacks have recently been developed to fool automatic speech recognition (ASR) systems. We here propose a defense against such attacks based on the uncertainty introduced by dropout in neural networks. We show that our defense is able to detect attacks created through optimized perturbations and frequency masking on a state-of-the-art end-to-end ASR system. Furthermore, the defense can be made robust against attacks that are immune to noise reduction. We test our defense on Mozilla's CommonVoice dataset, the UrbanSound dataset, and an excerpt of the LibriSpeech dataset, showing that it achieves high detection accuracy in a wide range of scenarios.