Cross-Representation Transferability of Adversarial Attacks: From Spectrograms to Audio Waveforms

This paper shows the susceptibility of spectrogram-based audio classifiers to adversarial attacks and the transferability of such attacks to audio waveforms. Some commonly used adversarial attacks to images have been applied to Mel-frequency and short-time Fourier transform spectrograms, and such pe...

Full description

Saved in:
Bibliographic Details
Published in2020 International Joint Conference on Neural Networks (IJCNN) pp. 1 - 7
Main Authors Michel Koerich, Karl, Esmailpour, Mohammad, Abdoli, Sajjad, Britto, Alceu de S., Koerich, Alessandro L.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2020
Subjects
Adversarial audio attacks
audio reconstruction
Computer architecture
Image reconstruction
Music
Perturbation methods
Spectrogram
Task analysis
transferability
Two dimensional displays
Online AccessGet full text

Cover

More Information
Summary:This paper shows the susceptibility of spectrogram-based audio classifiers to adversarial attacks and the transferability of such attacks to audio waveforms. Some commonly used adversarial attacks to images have been applied to Mel-frequency and short-time Fourier transform spectrograms, and such perturbed spectrograms are able to fool a 2D convolutional neural network (CNN). Such attacks produce perturbed spectrograms that are visually imperceptible by humans. Furthermore, the audio waveforms reconstructed from the perturbed spectrograms are also able to fool a 1D CNN trained on the original audio. Experimental results on a dataset of western music have shown that the 2D CNN achieves up to 81.87% of mean accuracy on legitimate examples and such performance drops to 12.09% on adversarial examples. Likewise, the 1D CNN achieves up to 78.29% of mean accuracy on original audio samples and such performance drops to 27.91% on adversarial audio waveforms reconstructed from the perturbed spectrograms.
ISSN:2161-4407
DOI:10.1109/IJCNN48605.2020.9207309