mlsanityData to 14 Oct 2026

Universal Adversarial Perturbations for Speech Recognition Systems

arXiv 1905.03828 ↗First posted 9 May 2019cs.LG cs.SD eess.AScited by 41

Not on the map. Why?

Abstract (arXiv)

In this work, we demonstrate the existence of universal adversarial audio perturbations that cause mis-transcription of audio signals by automatic speech recognition (ASR) systems. We propose an algorithm to find a single quasi-imperceptible perturbation, which when added to any arbitrary speech signal, will most likely fool the victim speech recognition model. Our experiments demonstrate the application of our proposed technique by crafting audio-agnostic universal perturbations for the state-of-the-art ASR system -- Mozilla DeepSpeech. Additionally, we show that such perturbations generalize to a significant extent across models that are not available during training, by performing a transferability test on a WaveNet based ASR system.

Key facts. Cited by 41 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 7; 2022: 5; 2023: 6; 2024: 10; 2025: 9; 2026: 4.

41 papers.

Sort:

By area:

  1. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  2. 2021A Survey On Universal Adversarial Attackcited by 59
  3. 2021WaveGuard: Understanding and Mitigating Audio Adversarial Examplescited by 40
  4. 2021Cross-modal Adversarial Reprogrammingcited by 34
  5. 2024Speech Robust Bench: A Robustness Benchmark For Speech Recognitioncited by 21
  6. 2023Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspectivecited by 20
  7. 2025AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Modelscited by 18
  8. 2024Muting Whisper: A Universal Acoustic Adversarial Attack on Speech Foundation Modelscited by 12
  9. 2025MixAT: Combining Continuous and Discrete Adversarial Training for LLMscited by 11
  10. 2021Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Modelscited by 10
  11. 2023Malafide: a novel adversarial convolutive noise attack against deepfake and spoofing detection systemscited by 10
  12. 2024XAI-Based Detection of Adversarial Attacks on Deepfake Detectorscited by 9
29 more
  1. 2024Who Can Withstand Chat-Audio Attacks? An Evaluation Benchmark for Large Audio-Language Modelscited by 7
  2. 2024Malacopula: adversarial automatic speaker verification attacks using a neural-based generalised Hammerstein modelcited by 6
  3. 2021Realizable Universal Adversarial Perturbations for Malwarecited by 5
  4. 2022Dictionary Attacks on Speaker Verificationcited by 5
  5. 2024ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Featurescited by 5
  6. 2021SoK: A Modularized Approach to Study the Security of Automatic Speech Recognition Systemscited by 4
  7. 2023MVPatch: More Vivid Patch for Adversarial Camouflaged Attacks on Object Detectors in the Physical Worldcited by 4
  8. 2024Transferable Adversarial Attacks against ASRcited by 4
  9. 2025When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputscited by 4
  10. 2025Breaking Audio Large Language Models by Attacking Only the Encoder: A Universal Targeted Latent-Space Audio Attackcited by 4
  11. 2024Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation Modelscited by 2
  12. 2025Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systemscited by 2
  13. 2021Catch Me If You Can: Blackbox Adversarial Attacks on Automatic Speech Recognition using Frequency Maskingcited by 1
  14. 2022Neural Predictor for Black-Box Adversarial Attacks on Speech Recognitioncited by 1
  15. 2022Adversarial Attacks on ASR Systems: An Overviewcited by 1
  16. 2022Universal Adversarial Directionscited by 1
  17. 2023Towards the Transferable Audio Adversarial Attack via Ensemble Methodscited by 1
  18. 2024STAA-Net: A Sparse and Transferable Adversarial Attack for Speech Emotion Recognitioncited by 1
  19. 2024Adversarially Robust Deepfake Detection via Adversarial Feature Similarity Learningcited by 1
  20. 2025Toward Understanding the Transferability of Adversarial Suffixes in Large Language Modelscited by 1
  21. 2022Analyzing Robustness of End-to-End Neural Models for Automatic Speech Recognitioncited by 0
  22. 2023AudioFool: Fast, Universal and synchronization-free Cross-Domain Attack on Speech Recognitioncited by 0
  23. 2025Are Deep Speech Denoising Models Robust to Adversarial Noise?cited by 0
  24. 2025Novel Loss-Enhanced Universal Adversarial Patches for Sustainable Speaker Privacycited by 0
  25. 2025ASRJam: Human-Friendly AI Speech Jamming to Prevent Automated Phone Scamscited by 0
  26. 2026Beyond Waveform Robustness: Robust Feature-Vocoder Adversarial Attacks on Automatic Speech Recognitioncited by 0
  27. 2026Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attackscited by 0
  28. 2026Audio-Driven Adversarial Defense for 3D Talking Face Generation with totally Visual Fidelity Preservationcited by 0
  29. 2026Psychoacoustically Aligned Latent Smoothing for Adversarial Robustness of Full-Duplex Speech-to-Speech Dialogue Modelscited by 0