mlsanityData to 7 Oct 2026

Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition

arXiv 1903.10346 ↗First posted 22 Mar 2019eess.AS cs.LG cs.SDcited by 123

Not on the map. Why?

Abstract (arXiv)

Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output. So far, adversarial examples have been studied most extensively in the image domain. In this domain, adversarial examples can be constructed by imperceptibly modifying images to cause misclassification, and are practical in the physical world. In contrast, current targeted adversarial examples applied to speech recognition systems have neither of these properties: humans can easily identify the adversarial perturbations, and they are not effective when played over-the-air. This paper makes advances on both of these fronts. First, we develop effectively imperceptible audio adversarial examples (verified through a human study) by leveraging the psychoacoustic principle of auditory masking, while retaining 100% targeted success rate on arbitrary full-sentence targets. Next, we make progress towards physical-world over-the-air audio adversarial examples by constructing perturbations which remain effective even after applying realistic simulated environmental distortions.

Key facts. Cited by 123 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 34; 2022: 27; 2023: 16; 2024: 17; 2025: 16; 2026: 13.

123 papers.

Sort:

By area:

  1. 2021Probabilistic Margins for Instance Reweighting in Adversarial Trainingcited by 57
  2. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 54
  3. 2021SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustnesscited by 49
  4. 2021WaveGuard: Understanding and Mitigating Audio Adversarial Examplescited by 39
  5. 2021Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attackscited by 33
  6. 2024AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Modelscited by 33
  7. 2021Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Informationcited by 25
  8. 2021Can audio-visual integration strengthen robustness under multimodal attacks?cited by 23
  9. 2022Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognitioncited by 22
  10. 2023Defending against Adversarial Audio via Diffusion Modelcited by 20
  11. 2023Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspectivecited by 19
  12. 2021Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learningcited by 16
38 more
  1. 2025AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Modelscited by 16
  2. 2021Targeted Attack on Deep RL-based Autonomous Driving with Learned Visual Patternscited by 13
  3. 2021Sequential Randomized Smoothing for Adversarially Robust Speech Recognitioncited by 13
  4. 2022Recent improvements of ASR models in the face of adversarial attackscited by 13
  5. 2022A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairnesscited by 13
  6. 2021Voting for the right answer: Adversarial defense for speaker verificationcited by 12
  7. 2021"Hello, It's Me": Deep Learning-based Speech Synthesis Attacks in the Real Worldcited by 12
  8. 2021Neural Population Geometry Reveals the Role of Stochasticity in Robust Perceptioncited by 12
  9. 2024Muting Whisper: A Universal Acoustic Adversarial Attack on Speech Foundation Modelscited by 12
  10. 2022There is more than one kind of robustness: Fooling Whisper with adversarial examplescited by 11
  11. 2025When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Modelscited by 11
  12. 2021Dompteur: Taming Audio Adversarial Examplescited by 10
  13. 2021Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Modelscited by 10
  14. 2021SoK: Machine Learning Governancecited by 9
  15. 2021AequeVox: Automated Fairness Testing of Speech Recognition Systemscited by 9
  16. 2024XAI-Based Detection of Adversarial Attacks on Deepfake Detectorscited by 9
  17. 2021Adversarial Sample Detection for Speaker Verification by Neural Vocoderscited by 8
  18. 2025"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Modelscited by 7
  19. 2021Real-Time Neural Voice Camouflagecited by 6
  20. 2022Visualizing Automatic Speech Recognition -- Means for a Better Understanding?cited by 6
  21. 2021Characterizing the adversarial vulnerability of speech self-supervised learningcited by 5
  22. 2022Dictionary Attacks on Speaker Verificationcited by 5
  23. 2023PhantomSound: Black-Box, Query-Efficient Audio Adversarial Attack via Split-Second Phoneme Injectioncited by 5
  24. 2024An Optimal Transport Approach for Computing Adversarial Training Lower Bounds in Multiclass Classificationcited by 5
  25. 2024SongBsAb: A Dual Prevention Approach against Singing Voice Conversion based Illegal Song Coverscited by 5
  26. 2021Multi-Discriminator Sobolev Defense-GAN Against Adversarial Attacks for End-to-End Speech Systemscited by 4
  27. 2021SoK: A Modularized Approach to Study the Security of Automatic Speech Recognition Systemscited by 4
  28. 2021Towards Making Deep Learning-based Vulnerability Detectors Robustcited by 4
  29. 2023Stealthy Physical Masked Face Recognition Attack via Adversarial Style Optimizationcited by 4
  30. 2024Low-Rank Adversarial PGD Attackcited by 4
  31. 2025TabAttackBench: A Benchmark for Adversarial Attacks on Tabular Datacited by 4
  32. 2021Towards Robust Speech-to-Text Adversarial Attackcited by 3
  33. 2021Fashion-Guided Adversarial Attack on Person Segmentationcited by 3
  34. 2021SEC4SR: A Security Analysis Platform for Speaker Recognitioncited by 3
  35. 2021Unity is strength: Improving the Detection of Adversarial Examples with Ensemble Approachescited by 3
  36. 2021Robustifying automatic speech recognition by extracting slowly varying featurescited by 3
  37. 2022Adversarial Machine Learning Threat Analysis and Remediation in Open Radio Access Network (O-RAN)cited by 3
  38. 2022Tubes Among Us: Analog Attack on Automatic Speaker Identificationcited by 3

50 most cited of 123 All 123 (JSON)