Universal Adversarial Perturbations for Speech Recognition Systems

05/09/2019
by   Paarth Neekhara, et al.
0

In this work, we demonstrate the existence of universal adversarial audio perturbations that cause mis-transcription of audio signals by automatic speech recognition (ASR) systems. We propose an algorithm to find a single quasi-imperceptible perturbation, which when added to any arbitrary speech signal, will most likely fool the victim speech recognition model. Our experiments demonstrate the application of our proposed technique by crafting audio-agnostic universal perturbations for the state-of-the-art ASR system -- Mozilla DeepSpeech. Additionally, we show that such perturbations generalize to a significant extent across models that are not available during training, by performing a transferability test on a WaveNet based ASR system.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/17/2019

Advancing Speech Recognition With No Speech Or With Noisy Speech

In this paper we demonstrate end to end continuous speech recognition (C...
research
04/06/2021

Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Models

Although end-to-end automatic speech recognition (e2e ASR) models are wi...
research
03/28/2023

TransAudio: Towards the Transferable Adversarial Audio Attack via Learning Contextualized Perturbations

In a transfer-based attack against Automatic Speech Recognition (ASR) sy...
research
12/18/2019

A Cycle-GAN Approach to Model Natural Perturbations in Speech for ASR Applications

Naturally introduced perturbations in audio signal, caused by emotional ...
research
06/01/2023

SlothSpeech: Denial-of-service Attack Against Speech Recognition Models

Deep Learning (DL) models have been popular nowadays to execute differen...
research
04/08/2019

Adversarial Audio: A New Information Hiding Method and Backdoor for DNN-based Speech Recognition Models

Audio is an important medium in people's daily life, hidden information ...
research
08/16/2018

Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding

Voice interfaces are becoming accepted widely as input methods for a div...

Please sign up or login with your details

Forgot password? Click here to reset