Characterizing Audio Adversarial Examples Using Temporal Dependency
Recent studies have highlighted adversarial examples as a ubiquitous threat to different neural network models and many downstream applications. Nonetheless, as unique data properties have inspired distinct and powerful learning principles, this paper aims to explore their potentials towards mitigating adversarial inputs. In particular, our results reveal the importance of using the temporal dependency in audio data to gain discriminate power against adversarial examples. Tested on the automatic speech recognition (ASR) tasks and three recent audio adversarial attacks, we find that (i) input transformation developed from image adversarial defense provides limited robustness improvement and is subtle to advanced attacks; (ii) temporal dependency can be exploited to gain discriminative power against audio adversarial examples and is resistant to adaptive attacks considered in our experiments. Our results not only show promising means of improving the robustness of ASR systems, but also offer novel insights in exploiting domain-specific data properties to mitigate negative effects of adversarial examples.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial DefenseAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Generating Robust Audio Adversarial Examples using Iterative Proportional Clipping
Audio adversarial examples, imperceptible to humans, have been constructed to attack automatic speech recognition (ASR) systems. However, the adversarial examples generated by existing approaches usually involve notable …
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionPush-Pull: Characterizing the Adversarial Robustness for Audio-Visual Active Speaker Detection
Audio-visual active speaker detection (AVASD) is well-developed, and now is an indispensable front-end for several multi-modal applications. However, to the best of our knowledge, the adversarial robustness of AVASD mode…
Active Speaker DetectionAdversarial RobustnessAudio-Visual Active Speaker DetectionCharacterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement
Recent studies have highlighted adversarial examples as ubiquitous threats to the deep neural network (DNN) based speech recognition systems. In this work, we present a U-Net based attention model, U-Net$_{At}$, to enhan…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data AugmentationSpeech Enhancement+2Detecting Adversarial Attacks On Audiovisual Speech Recognition
Adversarial attacks pose a threat to deep learning models. However, research on adversarial detection methods, especially in the multi-modal domain, is very limited. In this work, we propose an efficient and straightforw…
Audio-Visual Speech Recognitionspeech-recognitionSpeech RecognitionVisual Speech RecognitionOn the Limitation of Local Intrinsic Dimensionality for Characterizing the Subspaces of Adversarial Examples
Understanding and characterizing the subspaces of adversarial examples aid in studying the robustness of deep neural networks (DNNs) to adversarial perturbations. Very recently, Ma et al. (ICLR 2018) proposed to use loca…