Class-Conditional Defense GAN Against End-to-End Speech Attacks
In this paper we propose a novel defense approach against end-to-end adversarial attacks developed to fool advanced speech-to-text systems such as DeepSpeech and Lingvo. Unlike conventional defense approaches, the proposed approach does not directly employ low-level transformations such as autoencoding a given input signal aiming at removing potential adversarial perturbation. Instead of that, we find an optimal input vector for a class conditional generative adversarial network through minimizing the relative chordal distance adjustment between a given test input and the generator network. Then, we reconstruct the 1D signal from the synthesized spectrogram and the original phase information derived from the given input signal. Hence, this reconstruction does not add any extra noise to the signal and according to our experimental results, our defense-GAN considerably outperforms conventional defense algorithms both in terms of word error rate and sentence level recognition accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
Generative Adversarial NetworkSentenceSpeech-to-TextSimilar Papers 제목 키워드 기반
Adversarial Attacks against Neural Networks in Audio Domain: Exploiting Principal Components
Adversarial attacks are inputs that are similar to original inputs but altered on purpose. Speech-to-text neural networks that are widely used today are prone to misclassify adversarial attacks. In this study, first, we …
ClassificationGeneral ClassificationSpeech-to-TextMel Frequency Spectral Domain Defenses against Adversarial Attacks on Speech Recognition Systems
A variety of recent works have looked into defenses for deep neural networks against adversarial attacks particularly within the image processing domain. Speech processing applications such as automatic speech recognitio…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionAdversarially Robust Classification by Conditional Generative Model Inversion
Most adversarial attack defense methods rely on obfuscating gradients. These methods are successful in defending against gradient-based attacks; however, they are easily circumvented by attacks which either do not use th…
Adversarial AttackClassificationmodelRobust classificationDetecting Audio Attacks on ASR Systems with Dropout Uncertainty
Various adversarial audio attacks have recently been developed to fool automatic speech recognition (ASR) systems. We here propose a defense against such attacks based on the uncertainty introduced by dropout in neural n…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionPerceptual-based deep-learning denoiser as a defense against adversarial attacks on ASR systems
In this paper we investigate speech denoising as a defense against adversarial attacks on automatic speech recognition (ASR) systems. Adversarial attacks attempt to force misclassification by adding small perturbations t…
Adversarial RobustnessAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Denoising+3