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

Authors: Karl Michel Koerich, Mohammad Esmaeilpour, Sajjad Abdoli, Alceu de Souza Britto Jr., Alessandro Lameiras Koerich
Published: 2019-10-22 | Updated: 2020-07-29

Source: https://arxiv.org/abs/1910.10106

PDF: https://arxiv.org/pdf/1910.10106

AIにより推定されたラベル

性能評価 敵対的移転性 対抗的学習

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

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 performance drops to 12.09 achieves up to 78.29 performance drops to 27.91 the perturbed spectrograms.