mlsanityData to 14 Oct 2026

RSD-GAN: Regularized Sobolev Defense GAN Against Speech-to-Text Adversarial Attacks

arXiv 2207.06858 ↗First posted 14 Jul 2022cs.SD cs.LG eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

This paper introduces a new synthesis-based defense algorithm for counteracting with a varieties of adversarial attacks developed for challenging the performance of the cutting-edge speech-to-text transcription systems. Our algorithm implements a Sobolev-based GAN and proposes a novel regularizer for effectively controlling over the functionality of the entire generative model, particularly the discriminator network during training. Our achieved results upon carrying out numerous experiments on the victim DeepSpeech, Kaldi, and Lingvo speech transcription systems corroborate the remarkable performance of our defense approach against a comprehensive range of targeted and non-targeted adversarial attacks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 48 references that are in the map. First posted on arXiv 14 Jul 2022.

Builds on

26 of 48 references.

References · 26

  1. 2022Generative Adversarial Networkscited by 5,627
  2. 2013Exact solutions to the nonlinear dynamics of learning in deep linear neural networkscited by 763
  3. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 464
  4. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 460
  5. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  6. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 274
  7. 2019Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognitioncited by 124
  8. 2016Mode Regularized Generative Adversarial Networkscited by 123
  9. 2017The Cramer Distance as a Solution to Biased Wasserstein Gradientscited by 119
  10. 2019Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modelingcited by 86
  11. 2018Robust Audio Adversarial Example for a Physical Attackcited by 44
  12. 2018Targeted Adversarial Examples for Black Box Audio Systemscited by 41
14 more
  1. 2017Sobolev GANcited by 29
  2. 2017Learning to Draw Samples with Amortized Stein Variational Gradient Descentcited by 28
  3. 2017Fisher GANcited by 22
  4. 2019Imperio: Robust Over-the-Air Adversarial Examples for Automatic Speech Recognition Systemscited by 16
  5. 2018ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audiocited by 12
  6. 2018A Multi-Discriminator CycleGAN for Unsupervised Non-Parallel Speech Domain Adaptationcited by 10
  7. 2021Dompteur: Taming Audio Adversarial Examplescited by 10
  8. 2018Adversarial Machine Learning And Speech Emotion Recognition: Utilizing Generative Adversarial Networks For Robustnesscited by 9
  9. 2019Detection of Adversarial Attacks and Characterization of Adversarial Subspacecited by 7
  10. 2020Class-Conditional Defense GAN Against End-to-End Speech Attackscited by 5
  11. 2021Multi-Discriminator Sobolev Defense-GAN Against Adversarial Attacks for End-to-End Speech Systemscited by 4
  12. 2021Towards Robust Speech-to-Text Adversarial Attackcited by 3
  13. 2021Cyclic Defense GAN Against Speech Adversarial Attackscited by 2
  14. 2022From Environmental Sound Representation to Robustness of 2D CNN Models Against Adversarial Attackscited by 1

Built on by

Not cited yet.