mlsanityData to 14 Oct 2026

AudioFool: Fast, Universal and synchronization-free Cross-Domain Attack on Speech Recognition

arXiv 2309.11462 ↗First posted 20 Sep 2023cs.CR cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Automatic Speech Recognition systems have been shown to be vulnerable to adversarial attacks that manipulate the command executed on the device. Recent research has focused on exploring methods to create such attacks, however, some issues relating to Over-The-Air (OTA) attacks have not been properly addressed. In our work, we examine the needed properties of robust attacks compatible with the OTA model, and we design a method of generating attacks with arbitrary such desired properties, namely the invariance to synchronization, and the robustness to filtering: this allows a Denial-of-Service (DoS) attack against ASR systems. We achieve these characteristics by constructing attacks in a modified frequency domain through an inverse Fourier transform. We evaluate our method on standard keyword classification tasks and analyze it in OTA, and we analyze the properties of the cross-domain attacks to explain the efficiency of the approach.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 29 references that are in the map. First posted on arXiv 20 Sep 2023.

Builds on

23 of 29 references.

References · 23

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  5. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  6. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  7. 2016Universal adversarial perturbationscited by 784
  8. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
  9. 2017One pixel attack for fooling deep neural networkscited by 582
  10. 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
  11. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 274
  12. 2017Pyroomacoustics: A Python package for audio room simulations and array processing algorithmscited by 132
11 more
  1. 2018Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separationcited by 125
  2. 2018SparseFool: a few pixels make a big differencecited by 94
  3. 2018AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmarkcited by 72
  4. 2017DolphinAtack: Inaudible Voice Commandscited by 69
  5. 2017Fast Feature Fool: A data independent approach to universal adversarial perturbationscited by 66
  6. 2018CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognitioncited by 66
  7. 2019Universal Adversarial Perturbations for Speech Recognition Systemscited by 41
  8. 2020Enabling Fast and Universal Audio Adversarial Attack Using Generative Modelcited by 32
  9. 2020Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systemscited by 26
  10. 2019Universal Adversarial Audio Perturbationscited by 11
  11. 2019Understanding the Effectiveness of Ultrasonic Microphone Jammercited by 3

Built on by

Not cited yet.