mlsanityData to 14 Oct 2026

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

arXiv 2306.00794 ↗First posted 1 Jun 2023cs.SD cs.CR cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 13 of its 19 references that are in the map. First posted on arXiv 1 Jun 2023.

Builds on

13 of 19 references.

References · 13

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  4. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 397
  5. 2020fairseq S2T: Fast Speech-to-Text Modeling with fairseqcited by 176
  6. 2018Adversarial Attacks on Node Embeddings via Graph Poisoningcited by 109
  7. 2022NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Modelscited by 50
  8. 2021Large-Scale Self- and Semi-Supervised Learning for Speech Translationcited by 36
  9. 2022DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networkscited by 17
  10. 2022LLMEffiChecker: Understanding and Testing Efficiency Degradation of Large Language Modelscited by 16
  11. 2017Comparison of Decoding Strategies for CTC Acoustic Modelscited by 13
  12. 2022EREBA: Black-box Energy Testing of Adaptive Neural Networkscited by 5
1 more
  1. 2022CorrGAN: Input Transformation Technique Against Natural Corruptionscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 2; 2026: 5.

10 papers.

  1. 2023RT-LM: Uncertainty-Aware Resource Management for Real-Time Inference of Language Modelscited by 11
  2. 2025Energy-Latency Attacks: A New Adversarial Threat to Deep Learningcited by 5
  3. 2024Transferable Adversarial Attacks against ASRcited by 4
  4. 2023Dynamic Neural Network is All You Need: Understanding the Robustness of Dynamic Mechanisms in Neural Networkscited by 1
  5. 2025Efficiency Robustness of Dynamic Deep Learning Systemscited by 1
  6. 2026MORE: Multi-Objective Adversarial Attacks on Speech Recognitioncited by 0
  7. 2026AESOP: Adversarial Execution-path Selection to Overload Deep Learning Pipelinescited by 0
  8. 2026Beyond Waveform Robustness: Robust Feature-Vocoder Adversarial Attacks on Automatic Speech Recognitioncited by 0
  9. 2026Never Stop Speaking: a Denial-of-Service Attack on End-to-End Speech Language Modelscited by 0
  10. 2026From Acoustic Sensing to Physical Actions: A Comprehensive Survey of Security Risks in Edge-Deployed Audio LLM-Based Agentscited by 0