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

arXiv: https://arxiv.org/abs/2207.06858 · HTML: https://mlsanity.com/paper/2207.06858/

## 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 (most cited first, 26 of 26)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Exact solutions to the nonlinear dynamics of learning in deep linear neural networks](https://mlsanity.com/paper/1312.6120/) (2013)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models](https://mlsanity.com/paper/1805.06605/) (2018)
- [Audio Adversarial Examples: Targeted Attacks on Speech-to-Text](https://mlsanity.com/paper/1801.01944/) (2018)
- [Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition](https://mlsanity.com/paper/1903.10346/) (2019)
- [Mode Regularized Generative Adversarial Networks](https://mlsanity.com/paper/1612.02136/) (2016)
- [The Cramer Distance as a Solution to Biased Wasserstein Gradients](https://mlsanity.com/paper/1705.10743/) (2017)
- [Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling](https://mlsanity.com/paper/1902.08295/) (2019)
- [Robust Audio Adversarial Example for a Physical Attack](https://mlsanity.com/paper/1810.11793/) (2018)
- [Targeted Adversarial Examples for Black Box Audio Systems](https://mlsanity.com/paper/1805.07820/) (2018)
- [Sobolev GAN](https://mlsanity.com/paper/1711.04894/) (2017)
- [Learning to Draw Samples with Amortized Stein Variational Gradient Descent](https://mlsanity.com/paper/1707.06626/) (2017)
- [Fisher GAN](https://mlsanity.com/paper/1705.09675/) (2017)
- [Imperio: Robust Over-the-Air Adversarial Examples for Automatic Speech Recognition Systems](https://mlsanity.com/paper/1908.01551/) (2019)
- [ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio](https://mlsanity.com/paper/1805.11852/) (2018)
- [A Multi-Discriminator CycleGAN for Unsupervised Non-Parallel Speech Domain Adaptation](https://mlsanity.com/paper/1804.00522/) (2018)
- [Dompteur: Taming Audio Adversarial Examples](https://mlsanity.com/paper/2102.05431/) (2021)
- [Adversarial Machine Learning And Speech Emotion Recognition: Utilizing Generative Adversarial Networks For Robustness](https://mlsanity.com/paper/1811.11402/) (2018)
- [Detection of Adversarial Attacks and Characterization of Adversarial Subspace](https://mlsanity.com/paper/1910.12084/) (2019)
- [Class-Conditional Defense GAN Against End-to-End Speech Attacks](https://mlsanity.com/paper/2010.11352/) (2020)
- [Multi-Discriminator Sobolev Defense-GAN Against Adversarial Attacks for End-to-End Speech Systems](https://mlsanity.com/paper/2103.08086/) (2021)
- [Towards Robust Speech-to-Text Adversarial Attack](https://mlsanity.com/paper/2103.08095/) (2021)
- [Cyclic Defense GAN Against Speech Adversarial Attacks](https://mlsanity.com/paper/2103.14717/) (2021)
- [From Environmental Sound Representation to Robustness of 2D CNN Models Against Adversarial Attacks](https://mlsanity.com/paper/2204.07018/) (2022)

## 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.