Are Deep Speech Denoising Models Robust to Adversarial Noise?

Will Schwarzer, Philip S. Thomas, Andrea Fanelli, Xiaoyu Liu
3/14/2025
cs.SDcs.LGeess.AS

No confident code implementation found for this paper. 2 possible matches can be shown below.

Abstract

Deep noise suppression (DNS) models enjoy widespread use throughout a variety of high-stakes speech applications. However, in this paper, we show that four recent DNS models can each be reduced to outputting unintelligible gibberish through the addition of imperceptible adversarial noise. Furthermore, our results show the near-term plausibility of targeted attacks, which could induce models to output arbitrary utterances, and over-the-air attacks. While the success of these attacks varies by model and setting, and attacks appear to be strongest when model-specific (i.e., white-box and non-transferable), our results highlight a pressing need for practical countermeasures in DNS systems.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 2 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Evaluating Similitude and Robustness of Deep Image Denoising Models via Adversarial Attack

83% match2023

Muting Whisper: A Universal Acoustic Adversarial Attack on Speech Foundation Models

82% match1 repo412024

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

82% match1 repo32023

STAA-Net: A Sparse and Transferable Adversarial Attack for Speech Emotion Recognition

81% match2024

Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems

81% match2025

A Comparative Evaluation of Deep Learning Models for Speech Enhancement in Real-World Noisy Environments

81% match1 repo12025

Cite this paper

@article{schwarzer2025deep,
  title  = {Are Deep Speech Denoising Models Robust to Adversarial Noise?},
  author = {Will Schwarzer and Philip S. Thomas and Andrea Fanelli and Xiaoyu Liu},
  year   = {2025},
  eprint = {2503.11627},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2503.11627v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2503.11627.svg)](https://codeofpaper.com/paper/2503.11627)

Discussion