Show simple item record

dc.contributor.authorSUBRAMANIAN, Ven_US
dc.contributor.authorBenetos, Een_US
dc.contributor.authorSandler, Men_US
dc.contributor.author4th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2019)en_US
dc.date.accessioned2019-09-13T10:19:10Z
dc.date.available2019-08-24en_US
dc.date.issued2019-10-25en_US
dc.identifier.urihttps://qmro.qmul.ac.uk/xmlui/handle/123456789/59658
dc.description.abstractAn adversarial attack is a method to generate perturbations to the input of a machine learning model in order to make the output of the model incorrect. The perturbed inputs are known as adversarial examples. In this paper, we investigate the robustness of adversarial examples to simple input transformations such as mp3 compression, resampling, white noise and reverb in the task of sound event classification. By performing this analysis, we aim to provide insights on strengths and weaknesses in current adversarial attack algorithms as well as provide a baseline for defenses against adversarial attacks. Our work shows that adversarial attacks are not robust to simple input transformations. White noise is the most consistent method to defend against adversarial attacks with a success rate of 73.72% averaged across all models and attack algorithms.en_US
dc.format.extent239 - 243en_US
dc.titleRobustness of Adversarial Attacks in Sound Event Classificationen_US
dc.typeConference Proceeding
dc.rights.holder© The Author(s) 2019
pubs.notesNot knownen_US
pubs.publication-statusAccepteden_US
pubs.publisher-urlhttp://dcase.community/workshop2019/en_US
dcterms.dateAccepted2019-08-24en_US
rioxxterms.funderDefault funderen_US
rioxxterms.identifier.projectDefault projecten_US
qmul.funderA Machine Learning Framework for Audio Analysis and Retrieval::Royal Academy of Engineeringen_US
qmul.funderA Machine Learning Framework for Audio Analysis and Retrieval::Royal Academy of Engineeringen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record