Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks Liu, Y, Ma, Xingjun, Bailey, J and Lu, F 2020, Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks, in ECCV 2020 : Proceedings of the 2020 European Conference of Computer Vision, Springer, Berlin, Germany, pp. 182-199, doi: 10.1007/978-3-030-58607-2_11. Attached Files Name Description MIMEType Size Downloads Title Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks Author(s) Liu, Y Ma, Xingjun orcid.org/0000-0003-2099-4973 Bailey, J Lu, F Conference name Computer Vision. European Conference (2020 : Glasgow, Scotland) Conference location Glasgow, Scotland Conference dates 23-28 Aug. 2020 Title of proceedings ECCV 2020 : Proceedings of the 2020 European Conference of Computer Vision Publication date 2020 Series Lecture Notes in Computer Science; v.12355 Start page 182 End page 199 Total pages 18 Publisher Springer Place of publication Berlin, Germany Keyword(s) Backdoor attack Natural reflection Deep neural networks CORE2020 A ISBN 9783030586065 ISSN 0302-9743 1611-3349 Language eng DOI 10.1007/978-3-030-58607-2_11 Indigenous content off HERDC Research category E1 Full written paper - refereed Persistent URL http://hdl.handle.net/10536/DRO/DU:30146558 Document type: Conference Paper Collections: Faculty of Science, Engineering and Built Environment School of Information Technology Related Links Link Description Connect to published version Go to link with your DU access privileges     Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved. Versions Version Filter Type Mon, 11 Jan 2021, 08:57:56 EST Tue, 12 Jan 2021, 04:01:16 EST Tue, 12 Jan 2021, 05:24:23 EST Tue, 16 Feb 2021, 12:57:33 EST Tue, 16 Feb 2021, 12:58:52 EST Tue, 16 Feb 2021, 15:05:52 EST Filtered Full Citation counts:   Cited 0 times in TR Web of Science Cited 0 times in Scopus Search Google Scholar Access Statistics: 11 Abstract Views, 0 File Downloads  -  Detailed Statistics Created: Mon, 11 Jan 2021, 08:57:56 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.