Perceptual-based deep-learning denoiser as a defense against adversarial attacks on ASR systems
arXiv:2107.05222
Abstract
In this paper we investigate speech denoising as a defense against adversarial attacks on automatic speech recognition (ASR) systems. Adversarial attacks attempt to force misclassification by adding small perturbations to the original speech signal. We propose to counteract this by employing a neural-network based denoiser as a pre-processor in the ASR pipeline. The denoiser is independent of the downstream ASR model, and thus can be rapidly deployed in existing systems. We found that training the denoisier using a perceptually motivated loss function resulted in increased adversarial robustness without compromising ASR performance on benign samples. Our defense was evaluated (as a part of the DARPA GARD program) on the 'Kenansville' attack strategy across a range of attack strengths and speech samples. An average improvement in Word Error Rate (WER) of about 7.7% was observed over the undefended model at 20 dB signal-to-noise-ratio (SNR) attack strength.
arXiv comment5 pages, 4 figures submitted to ASRU 2021
References in corpus (4)
- Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
- Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
- The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Speech Quality and Testing Framework
- Adversarial Attacks and Defenses for Speech Recognition Systems