There is more than one kind of robustness: Fooling Whisper with adversarial examples

10/26/2022
by   Raphael Olivier, et al.
0

Whisper is a recent Automatic Speech Recognition (ASR) model displaying impressive robustness to both out-of-distribution inputs and random noise. In this work, we show that this robustness does not carry over to adversarial noise. We generate very small input perturbations with Signal Noise Ratio of up to 45dB, with which we can degrade Whisper performance dramatically, or even transcribe a target sentence of our choice. We also show that by fooling the Whisper language detector we can very easily degrade the performance of multilingual models. These vulnerabilities of a widely popular open-source model have practical security implications, and emphasize the need for adversarially robust ASR.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/31/2021

Adversarial Example Devastation and Detection on Speech Recognition System by Adding Random Noise

An automatic speech recognition (ASR) system based on a deep neural netw...
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
02/17/2022

Mitigating Closed-model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition

In this work, we aim to enhance the system robustness of end-to-end auto...
research
07/25/2020

MP3 Compression To Diminish Adversarial Noise in End-to-End Speech Recognition

Audio Adversarial Examples (AAE) represent specially created inputs mean...
research
09/17/2022

Watch What You Pretrain For: Targeted, Transferable Adversarial Examples on Self-Supervised Speech Recognition models

A targeted adversarial attack produces audio samples that can force an A...
research
02/13/2019

Enhanced Robot Speech Recognition Using Biomimetic Binaural Sound Source Localization

Inspired by the behavior of humans talking in noisy environments, we pro...
research
02/10/2021

Dompteur: Taming Audio Adversarial Examples

Adversarial examples seem to be inevitable. These specifically crafted i...

Please sign up or login with your details

Forgot password? Click here to reset