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

Abstract

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.

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyesmaeilpour2022rsd

Related papers

• Multi-discriminator Sobolev Defense-gan Against Adversarial Attacks For End-to-end Speech Systems (2021)8.82
• Class-conditional Defense GAN Against End-to-end Speech Attacks (2020)7.50
• Robust Speech Recognition Using Generative Adversarial Networks (2017)11.29
• High Fidelity Speech Synthesis With Adversarial Networks (2019)0.00
• Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks (2017)16.21
• Adversarial Machine Learning And Speech Emotion Recognition: Utilizing Generative Adversarial Networks For Robustness (2018)0.00
• Exploring Speech Enhancement With Generative Adversarial Networks For Robust Speech Recognition (2017)16.14
• Towards Generalized Speech Enhancement With Generative Adversarial Networks (2019)10.35