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

Mirazul Haque, Rutvij Shah, Simin Chen, Berrak Şişman, Cong Liu +1 more
6/1/2023
cs.SDcs.CRcs.LG

No official code found. Best implementation: 0xrutvij/SlothSpeech (3 stars, MIT, last commit 2023-03-09).

Abstract

Deep Learning (DL) models have been popular nowadays to execute different speech-related tasks, including automatic speech recognition (ASR). As ASR is being used in different real-time scenarios, it is important that the ASR model remains efficient against minor perturbations to the input. Hence, evaluating efficiency robustness of the ASR model is the need of the hour. We show that popular ASR models like Speech2Text model and Whisper model have dynamic computation based on different inputs, causing dynamic efficiency. In this work, we propose SlothSpeech, a denial-of-service attack against ASR models, which exploits the dynamic behaviour of the model. SlothSpeech uses the probability distribution of the output text tokens to generate perturbations to the audio such that efficiency of the ASR model is decreased. We find that SlothSpeech generated inputs can increase the latency up to 40X times the latency induced by benign input.

View on arXivView PDF

Code Implementations(1)

0xrutvij/SlothSpeechCommunity100%
MIT

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

31PythonMar 9, 20233 years agoMIT

Similar Papers

DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distribution

84% match1 repo12023

ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Features

84% match1 repo142024

ASRJam: Human-Friendly AI Speech Jamming to Prevent Automated Phone Scams

84% match2025

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

83% match1 repo412024

Noise Masking Attacks and Defenses for Pretrained Speech Models

83% match2024

Comparative Study on Noise-Augmented Training and its Effect on Adversarial Robustness in ASR Systems

83% match2024

Cite this paper

@article{haque2023slothspeech,
  title  = {SlothSpeech: Denial-of-service Attack Against Speech Recognition Models},
  author = {Mirazul Haque and Rutvij Shah and Simin Chen and Berrak Şişman and Cong Liu and Wei Yang},
  year   = {2023},
  eprint = {2306.00794},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.00794v1}
}

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/2306.00794.svg)](https://codeofpaper.com/paper/2306.00794)

Discussion