{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:31:27Z","timestamp":1730266287392,"version":"3.28.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892561","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"01-07","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Modal Adversarial Example Detection with Transformer"],"prefix":"10.1109","author":[{"given":"Chaoyue","family":"Ding","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University,Shanghai,China,200062"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiliang","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University,Shanghai,China,200062"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University,Shanghai,China,200062"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1286"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533328"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6484"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107024"},{"key":"ref31","first-page":"4835","article-title":"Deep multimodal fusion by channel exchanging","author":"wang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.09.039"},{"key":"ref37","article-title":"Deep contextualized word representations. arxiv 2018","volume":"12","author":"peters","year":"0","journal-title":"ArXiv Preprint"},{"journal-title":"Mozilla Common Voice Datasets","year":"2019","key":"ref36"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268937"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155389"},{"key":"ref10","article-title":"Did you hear that? adversarial examples against automatic speech recognition","author":"alzantot","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00009"},{"key":"ref12","first-page":"3102","article-title":"Adversarial example detection by classification for deep speech recognition","author":"samizade","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref13","article-title":"Characterizing audio adversarial examples using temporal dependency","author":"yang","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.clinicalnlp-1.29"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IEMTRONICS52119.2021.9422616"},{"key":"ref16","article-title":"Towards deep neural network architectures robust to adversarial examples","author":"gu","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00191"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00079"},{"key":"ref19","article-title":"Smooth adversarial training","author":"xie","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534148"},{"key":"ref4","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.11.011"},{"key":"ref3","first-page":"7829","article-title":"Transformer transducer: A streamable speech recognition model with transformer encoders and rnn-t loss","author":"zhang","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533769"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339678"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534444"},{"key":"ref8","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref7","article-title":"Intriguing properties of neural networks","author":"szegedy","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref2","first-page":"7303","article-title":"A sequential contrastive learning framework for robust dysarthric speech recognition","author":"wu","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207635"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506613"},{"key":"ref22","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050057"},{"key":"ref24","first-page":"10347","article-title":"Training data-efficient image Transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"ICML"},{"key":"ref23","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"ICLRE"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892561.pdf?arnumber=9892561","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T20:52:30Z","timestamp":1665780750000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892561\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892561","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}