mlsanityData to 14 Oct 2026

DolphinAtack: Inaudible Voice Commands

arXiv 1708.09537 ↗First posted 31 Aug 2017cs.CRcited by 69

Not on the map. Why?

Abstract (arXiv)

Speech recognition (SR) systems such as Siri or Google Now have become an increasingly popular human-computer interaction method, and have turned various systems into voice controllable systems(VCS). Prior work on attacking VCS shows that the hidden voice commands that are incomprehensible to people can control the systems. Hidden voice commands, though hidden, are nonetheless audible. In this work, we design a completely inaudible attack, DolphinAttack, that modulates voice commands on ultrasonic carriers (e.g., f > 20 kHz) to achieve inaudibility. By leveraging the nonlinearity of the microphone circuits, the modulated low frequency audio commands can be successfully demodulated, recovered, and more importantly interpreted by the speech recognition systems. We validate DolphinAttack on popular speech recognition systems, including Siri, Google Now, Samsung S Voice, Huawei HiVoice, Cortana and Alexa. By injecting a sequence of inaudible voice commands, we show a few proof-of-concept attacks, which include activating Siri to initiate a FaceTime call on iPhone, activating Google Now to switch the phone to the airplane mode, and even manipulating the navigation system in an Audi automobile. We propose hardware and software defense solutions. We validate that it is feasible to detect DolphinAttack by classifying the audios using supported vector machine (SVM), and suggest to re-design voice controllable systems to be resilient to inaudible voice command attacks.

Key facts. Cited by 69 papers in the map (data through 14 Oct 2026). First posted on arXiv 31 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 18; 2022: 11; 2023: 15; 2024: 6; 2025: 8; 2026: 11.

69 papers.

Sort:

By area:

  1. 2021Can You Hear It? Backdoor Attacks via Ultrasonic Triggerscited by 44
  2. 2025Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attackscited by 34
  3. 2021Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Informationcited by 25
  4. 2021Can audio-visual integration strengthen robustness under multimodal attacks?cited by 23
  5. 2022Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognitioncited by 23
  6. 2021They See Me Rollin': Inherent Vulnerability of the Rolling Shutter in CMOS Image Sensorscited by 17
  7. 2021Widening Access to Applied Machine Learning with TinyMLcited by 17
  8. 2024LLM Whisperer: An Inconspicuous Attack to Bias LLM Responsescited by 15
  9. 2024Easier Said Than Done: Unpacking Intent-Behavior Gap in Jailbreaking LLM-Based Robotscited by 15
  10. 2021Sequential Randomized Smoothing for Adversarially Robust Speech Recognitioncited by 13
  11. 2021Adversarial Machine Learning for 5G Communications Securitycited by 12
  12. 2021Fundamental Tradeoffs in Distributionally Adversarial Trainingcited by 12
38 more
  1. 2024Muting Whisper: A Universal Acoustic Adversarial Attack on Speech Foundation Modelscited by 12
  2. 2021Dompteur: Taming Audio Adversarial Examplescited by 10
  3. 2023QFA2SR: Query-Free Adversarial Transfer Attacks to Speaker Recognition Systemscited by 9
  4. 2025Phantom Menace: Exploring and Enhancing the Robustness of VLA Models Against Physical Sensor Attackscited by 9
  5. 2021Adversarial robustness for latent models: Revisiting the robust-standard accuracies tradeoffcited by 8
  6. 2023"Alexa doesn't have that many feelings": Children's understanding of AI through interactions with smart speakers in their homescited by 8
  7. 2023Chatbots to ChatGPT in a Cybersecurity Space: Evolution, Vulnerabilities, Attacks, Challenges, and Future Recommendationscited by 8
  8. 2023MASTERKEY: Practical Backdoor Attack Against Speaker Verification Systemscited by 8
  9. 2023Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systemscited by 6
  10. 2023Enrollment-stage Backdoor Attacks on Speaker Recognition Systems via Adversarial Ultrasoundcited by 5
  11. 2023PhantomSound: Black-Box, Query-Efficient Audio Adversarial Attack via Split-Second Phoneme Injectioncited by 5
  12. 2024ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Featurescited by 5
  13. 2021SoK: A Modularized Approach to Study the Security of Automatic Speech Recognition Systemscited by 4
  14. 2022Unlabeled Data Help: Minimax Analysis and Adversarial Robustnesscited by 4
  15. 2026Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Surveycited by 4
  16. 2021FakeWake: Understanding and Mitigating Fake Wake-up Words of Voice Assistantscited by 3
  17. 2022Adversarial Attacks on Speech Recognition Systems for Mission-Critical Applications: A Surveycited by 3
  18. 2022Perception-Aware Attack: Creating Adversarial Music via Reverse-Engineering Human Perceptioncited by 3
  19. 2022Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Surveycited by 3
  20. 2023Security and Privacy Problems in Voice Assistant Applications: A Surveycited by 3
  21. 2022SuperVoice: Text-Independent Speaker Verification Using Ultrasound Energy in Human Speechcited by 2
  22. 2022Privacy against Real-Time Speech Emotion Detection via Acoustic Adversarial Evasion of Machine Learningcited by 2
  23. 2024Deep Learning Approaches for Detecting Adversarial Cyberbullying and Hate Speech in Social Networkscited by 2
  24. 2021Robust Sensor Fusion Algorithms Against Voice Command Attacks in Autonomous Vehiclescited by 1
  25. 2022Attacks as Defenses: Designing Robust Audio CAPTCHAs Using Attacks on Automatic Speech Recognition Systemscited by 1
  26. 2022Disappeared Command: Spoofing Attack On Automatic Speech Recognition Systems with Sound Maskingcited by 1
  27. 2022Adversarial Attacks on ASR Systems: An Overviewcited by 1
  28. 2023NUANCE: Near Ultrasound Attack On Networked Communication Environmentscited by 1
  29. 2023Trustworthy Sensor Fusion against Inaudible Command Attacks in Advanced Driver-Assistance Systemcited by 1
  30. 2025LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systemscited by 1
  31. 2025Impact of Phonetics on Speaker Identity in Adversarial Voice Attackcited by 1
  32. 2025AegisAgent: An Autonomous Defense Agent Against Prompt Injection Attacks in LLM-HARscited by 1
  33. 2026Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMscited by 1
  34. 2026Semantic Denial of Service in LLM-controlled robotscited by 1
  35. 2026Codec-Robust Attacks on Audio LLMscited by 1
  36. 2021Practical Speech Re-use Prevention in Voice-driven Servicescited by 0
  37. 2021Audio Adversarial Examples: Attacks Using Vocal Maskscited by 0
  38. 2021Audio Attacks and Defenses against AED Systems -- A Practical Studycited by 0

50 most cited of 69 All 69 (JSON)