Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 270

The DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.

Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding

Open access
Schonherr, Lea, Kohls, Katharina, Zeiler, Steffen, Holz, Thorsten, Kolossa, Dorothea·2019·Proceedings 2019 Network and Distributed System Security Symposium

Abstract

Voice interfaces are becoming accepted widely as input methods for a diverse set of devices.This development is driven by rapid improvements in automatic speech recognition (ASR), which now performs on par with human listening in many tasks.These improvements base on an ongoing evolution of deep neural networks (DNNs) as the computational core of ASR.However, recent research results show that DNNs are vulnerable to adversarial perturbations, which allow attackers to force the transcription into a malicious output.In this paper, we introduce a new type of adversarial examples based on psychoacoustic hiding.Our attack exploits the characteristics of DNN-based ASR systems, where we extend the original analysis procedure by an additional backpropagation step.We use this backpropagation to learn the degrees of freedom for the adversarial perturbation of the input signal, i.e., we apply a psychoacoustic model and manipulate the acoustic signal below the thresholds of human perception.To further minimize the perceptibility of the perturbations, we use forced alignment to find the best fitting temporal alignment between the original audio sample and the malicious target transcription.These extensions allow us to embed an arbitrary audio input with a malicious voice command that is then transcribed by the ASR system, with the audio signal remaining barely distinguishable from the original signal.In an experimental evaluation, we attack the stateof-the-art speech recognition system Kaldi and determine the best performing parameter and analysis setup for different types of input.Our results show that we are successful in up to 98 % of cases with a computational effort of fewer than two minutes for a ten-second audio file.Based on user studies, we found that none of our target transcriptions were audible to human listeners, who still understand the original speech content with unchanged accuracy.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.14722/ndss.2019.23288

Cites

37 of 37 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 37 references

Cited by

See all 270

Metadata

Authors
Schonherr, L., Kohls, K., Zeiler, S., Holz, T., & Kolossa, D.
Venue
Proceedings 2019 Network and Distributed System Security Symposium
Published
2019
OpenAlex
W2885407017
Cited by
270
References
37
FWCI
16.53
Type
conference paper
Language
en
Open access
bronze

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding. https://app.cochat.ai/papers/10.14722/ndss.2019.23288
The paper
Schonherr, L., Kohls, K., Zeiler, S., Holz, T., & Kolossa, D. (2019). Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding. Proceedings 2019 Network and Distributed System Security Symposium. https://doi.org/10.14722/ndss.2019.23288

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.