paper-with-me

Papers

Defense against Adversarial Attacks on Hybrid Speech Recognition using Joint Adversarial Fine-tuning with Denoiser

2022-04-08 · Sonal Joshi, Saurabh Kataria, Yiwen Shao, Piotr Zelasko, Jesus Villalba, Sanjeev Khudanpur, Najim Dehak

Adversarial attacks are a threat to automatic speech recognition (ASR) systems, and it becomes imperative to propose defenses to protect them. In this paper, we perform experiments to show that K2 conformer hybrid ASR is strongly affected by white-box adversarial attacks. We propose three defenses--denoiser pre-processor, adversarially fine-tuning ASR model, and adversarially fine-tuning joint model of ASR and denoiser. Our evaluation shows denoiser pre-processor (trained on offline adversarial examples) fails to defend against adaptive white-box attacks. However, adversarially fine-tuning the denoiser using a tandem model of denoiser and ASR offers more robustness. We evaluate two variants of this defense--one updating parameters of both models and the second keeping ASR frozen. The joint model offers a mean absolute decrease of 19.3\% ground truth (GT) WER with reference to baseline against fast gradient sign method (FGSM) attacks with different $L_\infty$ norms. The joint model with frozen ASR parameters gives the best defense against projected gradient descent (PGD) with 7 iterations, yielding a mean absolute increase of 22.3\% GT WER with reference to baseline; and against PGD with 500 iterations, yielding a mean absolute decrease of 45.08\% GT WER and an increase of 68.05\% adversarial target WER.

📄 PDF Abstract BibTeX arXiv:2204.03851

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

MIXPGD: Hybrid Adversarial Training for Speech Recognition Systems

2023-03-10 · Aminul Huq, Weiyi Zhang, Xiaolin Hu

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. I…

Adversarial AttackAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognition+1

Mel Frequency Spectral Domain Defenses against Adversarial Attacks on Speech Recognition Systems

2022-03-29 · Nicholas Mehlman, Anirudh Sreeram, Raghuveer Peri, Shrikanth Narayanan

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 Recognition

Adversarial defense for deep speaker recognition using hybrid adversarial training

2020-10-30

Deep neural network based speaker recognition systems can easily be deceived by an adversary using minuscule imperceptible perturbations to the input speech samples. These adversarial attacks pose serious security threat…

Adversarial DefenseSpeaker Recognition

Adversarial Attacks against Neural Networks in Audio Domain: Exploiting Principal Components

2020-07-14 · Ken Alparslan, Yigit Alparslan, Matthew Burlick

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-Text

The defender's perspective on automatic speaker verification: An overview

2023-05-22 · Haibin Wu, Jiawen Kang, Lingwei Meng, Helen Meng 외

Automatic speaker verification (ASV) plays a critical role in security-sensitive environments. Regrettably, the reliability of ASV has been undermined by the emergence of spoofing attacks, such as replay and synthetic sp…

Speaker Verification