RSD-GAN: Regularized Sobolev Defense GAN Against Speech-to-Text Adversarial Attacks
| Autor: | Mohammad Esmaeilpour, Nourhene Chaalia, Patrick Cardinal |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Sound (cs.SD) Audio and Speech Processing (eess.AS) Applied Mathematics Signal Processing FOS: Electrical engineering electronic engineering information engineering Electrical and Electronic Engineering Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing Machine Learning (cs.LG) |
| DOI: | 10.48550/arxiv.2207.06858 |
| Popis: | 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. Comment: Paper ACCEPTED FOR PUBLICATION IEEE Signal Processing Letters Journal |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|