A Robust Approach for Securing Audio Classification Against Adversarial Attacks

Adversarial audio attacks can be considered as a small perturbation unperceptive to human ears that is intentionally added to an audio signal and causes a machine learning model to make mistakes. This poses a security concern about the safety of machine learning models since the adversarial attacks...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on information forensics and security Vol. 15; pp. 2147 - 2159
Main Authors:	Esmaeilpour, Mohammad, Cardinal, Patrick, Lameiras Koerich, Alessandro
Format:	Journal Article
Language:	English
Published:	New York IEEE 2020 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	adversarial attack Algorithms Artificial neural networks Audio signals Background noise Classification convolutional denoising autoencoder Discrete Wavelet Transform environmental sound classification Feature extraction Fourier transforms K-means Machine learning Optimization Perturbation Perturbation methods Predictive models Representations Resilience Robustness Signal processing Spectrograms Support vector machines support vector machines (SVM) Two dimensional displays Two dimensional models Wavelet transforms
ISSN:	1556-6013, 1556-6021
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!