{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:21:46Z","timestamp":1753600906869,"version":"3.37.3"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746124","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"231-235","source":"Crossref","is-referenced-by-count":4,"title":["On Adversarial Robustness Of Large-Scale Audio Visual Learning"],"prefix":"10.1109","author":[{"given":"Juncheng B","family":"Li","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Shuhui","family":"Qu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Xinjian","family":"Li","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Po-Yao Bernie","family":"Huang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Florian","family":"Metze","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00039"},{"article-title":"Large-scale adversarial training for vision-and-language representation learning","year":"2020","author":"gan","key":"ref11"},{"key":"ref12","article-title":"Empir: Ensembles of mixed precision deep networks for increased robustness against adversarial attacks","author":"sen","year":"2020","journal-title":"ICLRE"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","year":"2012","author":"soomro","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"article-title":"Appendix: On adversarial robustness of large-scale audio visual learning","year":"2021","author":"li","key":"ref17"},{"article-title":"Volumes of n-dimensional spheres and ellipsoids","year":"0","author":"jorgensen","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00035"},{"article-title":"On evaluating adversarial robustness","year":"2019","author":"carlini","key":"ref4"},{"key":"ref3","first-page":"1765","article-title":"Universal adversarial perturbations","author":"moosavi-dezfooli","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref6","first-page":"5286","article-title":"Provable defenses against adversarial examples via the convex outer adversarial polytope","author":"wong","year":"2018","journal-title":"International Conference on Machine Learning"},{"journal-title":"Robustness May be at odds with accuracy","year":"2018","author":"tsipras","key":"ref5"},{"article-title":"Certified adversarial robustness via randomized smoothing","year":"2019","author":"cohen","key":"ref8"},{"key":"ref7","first-page":"14082","article-title":"Provable certificates for adversarial examples: Fitting a ball in the union of polytopes","author":"jordan","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"article-title":"Towards deep learning models resistant to adversarial attacks","year":"2017","author":"madry","key":"ref9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"article-title":"Fast is better than free: Revisiting adversarial training","year":"2020","author":"wong","key":"ref22"},{"article-title":"The kinetics human action video dataset","year":"2017","author":"kay","key":"ref21"},{"article-title":"Panns: Large-scale pretrained audio neural networks for audio pattern recognition","year":"2019","author":"kong","key":"ref23"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746124.pdf?arnumber=9746124","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:39Z","timestamp":1660594059000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746124\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746124","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}