Show simple item record

dc.contributor.authorSUBRAMANIAN, Ven_US
dc.contributor.authorPankajakshan, Aen_US
dc.contributor.authorBenetos, Een_US
dc.contributor.authorXu, Nen_US
dc.contributor.authorMcDonald, Sen_US
dc.contributor.authorSandler, Men_US
dc.contributor.authorIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2020)en_US
dc.date.accessioned2020-03-19T13:34:26Z
dc.date.available2020-01-24en_US
dc.date.issued2020-05-04en_US
dc.identifier.urihttps://qmro.qmul.ac.uk/xmlui/handle/123456789/63241
dc.description.abstractAn adversarial attack is an algorithm that perturbs the input of a machine learning model in an intelligent way in order to change the output of the model. An important property of adversarial attacks is transferability. According to this property, it is possible to generate adversarial perturbations on one model and apply it the input to fool the output of a different model. Our work focuses on studying the transferability of adversarial attacks in sound event classification. We are able to demonstrate differences in transferability properties from those observed in computer vision. We show that dataset normalization techniques such as z-score normalization does not affect the transferability of adversarial attacks and we show that techniques such as knowledge distillation do not increase the transferability of attacks.en_US
dc.format.extent? - ? (5)en_US
dc.publisherIEEEen_US
dc.titleA Study on the Transferability of Adversarial Attacks in Sound Event Classificationen_US
dc.typeConference Proceeding
dc.rights.holder© IEEE 2020
pubs.notesNot knownen_US
pubs.publication-statusAccepteden_US
pubs.publisher-urlhttps://2020.ieeeicassp.org/en_US
dcterms.dateAccepted2020-01-24en_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