paper-with-me

홈 › Papers

Adversarial Attacks and Defenses for Speech Recognition Systems

2021-03-31 · Piotr Żelasko, Sonal Joshi, Yiwen Shao, Jesus Villalba, Jan Trmal, Najim Dehak, Sanjeev Khudanpur

The ubiquitous presence of machine learning systems in our lives necessitates research into their vulnerabilities and appropriate countermeasures. In particular, we investigate the effectiveness of adversarial attacks and defenses against automatic speech recognition (ASR) systems. We select two ASR models - a thoroughly studied DeepSpeech model and a more recent Espresso framework Transformer encoder-decoder model. We investigate two threat models: a denial-of-service scenario where fast gradient-sign method (FGSM) or weak projected gradient descent (PGD) attacks are used to degrade the model's word error rate (WER); and a targeted scenario where a more potent imperceptible attack forces the system to recognize a specific phrase. We find that the attack transferability across the investigated ASR systems is limited. To defend the model, we use two preprocessing defenses: randomized smoothing and WaveGAN-based vocoder, and find that they significantly improve the model's adversarial robustness. We show that a WaveGAN vocoder can be a useful countermeasure to adversarial attacks on ASR systems - even when it is jointly attacked with the ASR, the target phrases' word error rate is high.

📄 PDF Abstract BibTeX arXiv:2103.17122

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Decoderspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Randomized Smoothing 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

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

Beyond Waveform Robustness: Robust Feature-Vocoder Adversarial Attacks on Automatic Speech Recognition

2026-06-04 · Yifan Liao, Zongmin Zhang, Zhen Sun, Yuhui Sun 외 arxiv

Automatic speech recognition (ASR) systems have become widely used for multilingual speech-to-text transcription. Their robustness to adversarial attacks has become an important topic for the community. Existing adversar…

Self-Supervised LearningSpeech Recognition

Study of Pre-processing Defenses against Adversarial Attacks on State-of-the-art Speaker Recognition Systems

2021-01-22 · Sonal Joshi, Jesús Villalba, Piotr Żelasko, Laureano Moro-Velázquez 외

Adversarial examples to speaker recognition (SR) systems are generated by adding a carefully crafted noise to the speech signal to make the system fail while being imperceptible to humans. Such attacks pose severe securi…

Speaker Recognition

Representation Learning to Classify and Detect Adversarial Attacks against Speaker and Speech Recognition Systems

2021-07-09 · Jesús Villalba, Sonal Joshi, Piotr Żelasko, Najim Dehak

Adversarial attacks have become a major threat for machine learning applications. There is a growing interest in studying these attacks in the audio domain, e.g, speech and speaker recognition; and find defenses against …

Representation LearningSpeaker IdentificationSpeaker RecognitionSpeaker Verification+2

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 외

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…

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