Weighted-Sampling Audio Adversarial Example Attack
Recent studies have highlighted audio adversarial examples as a ubiquitous threat to state-of-the-art automatic speech recognition systems. Thorough studies on how to effectively generate adversarial examples are essential to prevent potential attacks. Despite many research on this, the efficiency and the robustness of existing works are not yet satisfactory. In this paper, we propose~\textit{weighted-sampling audio adversarial examples}, focusing on the numbers and the weights of distortion to reinforce the attack. Further, we apply a denoising method in the loss function to make the adversarial attack more imperceptible. Experiments show that our method is the first in the field to generate audio adversarial examples with low noise and high audio robustness at the minute time-consuming level.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Denoisingspeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
PhaseFool: Phase-oriented Audio Adversarial Examples via Energy Dissipation
Audio adversarial attacks design perturbations onto inputs that lead an automatic speech recognition (ASR) model to predict incorrect outputs. Current audio adversarial attacks optimize perturbations with different const…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Sentencespeech-recognition+1Audio Injection Adversarial Example Attack
We study the problem of audio adversarial example attacks with sparse perturbations. Compared with image adversarial example attacks, attacking audio is more challenging because the audio structure is more complex and th…
Audio Adversarial Examples: Attacks Using Vocal Masks
We construct audio adversarial examples on automatic Speech-To-Text systems . Given any audio waveform, we produce an another by overlaying an audio vocal mask generated from the original audio. We apply our audio advers…
Adversarial AttackSpeech-to-TextAudio Adversarial Examples: Targeted Attacks on Speech-to-Text
We construct targeted audio adversarial examples on automatic speech recognition. Given any audio waveform, we can produce another that is over 99.9% similar, but transcribes as any phrase we choose (recognizing up to 50…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+1Robust Audio Adversarial Example for a Physical Attack
We propose a method to generate audio adversarial examples that can attack a state-of-the-art speech recognition model in the physical world. Previous work assumes that generated adversarial examples are directly fed to …
speech-recognitionSpeech Recognition