{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T12:27:40Z","timestamp":1725625660236},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T00:00:00Z","timestamp":1662940800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T00:00:00Z","timestamp":1662940800000},"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":[[2022,9,12]]},"DOI":"10.1109\/dasc\/picom\/cbdcom\/cy55231.2022.9927771","type":"proceedings-article","created":{"date-parts":[[2022,12,13]],"date-time":"2022-12-13T14:43:02Z","timestamp":1670942582000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["SanitAIs: Unsupervised Data Augmentation to Sanitize Trojaned Neural Networks"],"prefix":"10.1109","author":[{"given":"Kiran","family":"Karra","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Applied Physics Laboratory,Laurel,MD,USA"}]},{"given":"Chace","family":"Ashcraft","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Applied Physics Laboratory,Laurel,MD,USA"}]},{"given":"Cash","family":"Costello","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Applied Physics Laboratory,Laurel,MD,USA"}]}],"member":"263","reference":[{"key":"ref10","first-page":"8803","article-title":"Loss surfaces, mode connectivity, and fast ensembling of dnns","author":"garipov","year":"2018","journal-title":"Proceedings of the 32Nd International Conference on Neural Information Processing Systems"},{"article-title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks","year":"2021","author":"li","key":"ref11"},{"key":"ref12","first-page":"1310","article-title":"Certified adversarial robustness via randomized smoothing","author":"cohen","year":"2019","journal-title":"International Conference on Machine Learning"},{"article-title":"The trojai software framework: An opensource tool for embedding trojans into deep learning models","year":"2020","author":"karra","key":"ref13"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref14"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"simonyan","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref17","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"article-title":"Maxup: A simple way to improve generalization of neural network training","year":"2020","author":"gong","key":"ref18"},{"key":"ref19","first-page":"6023","article-title":"Cutmix: Regularization strategy to train strong classifiers with localizable features","author":"yun","year":"2019","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2941376"},{"article-title":"Clean-label backdoor attacks","year":"2018","author":"turner","key":"ref3"},{"article-title":"Unsupervised data augmentation for consistency training","year":"2019","author":"xie","key":"ref6"},{"year":"2019","key":"ref5","article-title":"Trojans in artificial intelligence (trojai)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00470-5_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2017.16"},{"article-title":"Potrojan: powerful neural-level trojan designs in deep learning models","year":"2018","author":"zou","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00031"},{"article-title":"Badnets: Identifying vulnerabilities in the machine learning model supply chain","year":"2017","author":"gu","key":"ref1"},{"article-title":"Comparing rewinding and fine-tuning in neural network pruning","year":"2020","author":"renda","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"Cinic-10 is not imagenet or cifar-10","year":"2018","author":"darlow","key":"ref21"},{"article-title":"Randaugment: Practical data augmentation with no separate search","year":"2019","author":"cubuk","key":"ref23"}],"event":{"name":"2022 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC\/PiCom\/CBDCom\/CyberSciTech)","start":{"date-parts":[[2022,9,12]]},"location":"Falerna, Italy","end":{"date-parts":[[2022,9,15]]}},"container-title":["2022 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC\/PiCom\/CBDCom\/CyberSciTech)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9927523\/9927699\/09927771.pdf?arnumber=9927771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,23]],"date-time":"2023-01-23T15:12:35Z","timestamp":1674486755000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9927771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,12]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/dasc\/picom\/cbdcom\/cy55231.2022.9927771","relation":{},"subject":[],"published":{"date-parts":[[2022,9,12]]}}}