# MIXPGD: Hybrid Adversarial Training for Speech Recognition Systems

arXiv: https://arxiv.org/abs/2303.05758 · HTML: https://mlsanity.com/paper/2303.05758/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 10 Mar 2023.

## Builds on (most cited first, 13 of 13)

- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Deep Learning for Sentiment Analysis : A Survey](https://mlsanity.com/paper/1801.07883/) (2018)
- [Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training](https://mlsanity.com/paper/1907.10764/) (2019)
- [Characterizing Audio Adversarial Examples Using Temporal Dependency](https://mlsanity.com/paper/1809.10875/) (2018)
- [Adversarial Attack and Defense Strategies for Deep Speaker Recognition Systems](https://mlsanity.com/paper/2008.07685/) (2020)
- [Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement](https://mlsanity.com/paper/2003.13917/) (2020)
- [Training Augmentation with Adversarial Examples for Robust Speech Recognition](https://mlsanity.com/paper/1806.02782/) (2018)
- [Detecting Adversarial Attacks On Audiovisual Speech Recognition](https://mlsanity.com/paper/1912.08639/) (2019)
- [End-to-End Face Parsing via Interlinked Convolutional Neural Networks](https://mlsanity.com/paper/2002.04831/) (2020)
- [MP3 Compression To Diminish Adversarial Noise in End-to-End Speech Recognition](https://mlsanity.com/paper/2007.12892/) (2020)
- [Detecting Audio Attacks on ASR Systems with Dropout Uncertainty](https://mlsanity.com/paper/2006.01906/) (2020)

## Built on by (most cited first, 1 of 1)

- [Improving Fast Adversarial Training with Prior-Guided Knowledge](https://mlsanity.com/paper/2304.00202/) (2023)

## Abstract (arXiv)

Automatic speech recognition (ASR) systems based on deep neural networks are weak against adversarial perturbations. We propose mixPGD adversarial training method to improve the robustness of the model for ASR systems. In standard adversarial training, adversarial samples are generated by leveraging supervised or unsupervised methods. We merge the capabilities of both supervised and unsupervised approaches in our method to generate new adversarial samples which aid in improving model robustness. Extensive experiments and comparison across various state-of-the-art defense methods and adversarial attacks have been performed to show that mixPGD gains 4.1% WER of better performance than previous best performing models under white-box adversarial attack setting. We tested our proposed defense method against both white-box and transfer based black-box attack settings to ensure that our defense strategy is robust against various types of attacks. Empirical results on several adversarial attacks validate the effectiveness of our proposed approach.