2019 · 18 citations · 20 references
ComputingCybersecurityAcousticsComputational AcousticsMachine LearningDeep LearningPattern RecognitionSpeech RecognitionAdversarial RobustnessAutomatic RecognitionNoise RobustnessRobust Speech RecognitionSpeech Signal AnalysisSpeech Signal ProcessingSpeech Spoofing DetectionVictim Recognition
In this work, we demonstrate the existence of universal adversarial audio perturbations that cause mis-transcription of audio signals by automatic speech recognition (ASR) systems. We propose an algorithm to find a single quasi-imperceptible perturbation, which when added to any arbitrary speech signal, will most likely fool the victim speech recognition model. Our experiments demonstrate the application of our proposed technique by crafting audio-agnostic universal perturbations for the state-of-the-art ASR system -- Mozilla DeepSpeech. Additionally, we show that such perturbations generalize to a significant extent across models that are not available during training, by performing a transferability test on a WaveNet based ASR system.
20
Connectionist temporal classification
Alex Graves, Santiago Fernández, Faustino Gomez et al. · 2006 · 5.4K citations
The Limitations of Deep Learning in Adversarial Settings
Nicolas Papernot, Patrick McDaniel, Somesh Jha et al. · 2016 · 3.9K citations