{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:00:52Z","timestamp":1780761652998,"version":"3.54.1"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-009"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-001"}],"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":[[2023,5]]},"DOI":"10.1109\/sp46215.2023.10179457","type":"proceedings-article","created":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T17:18:15Z","timestamp":1689959895000},"page":"1944-1960","source":"Crossref","is-referenced-by-count":7,"title":["Spectral-DP: Differentially Private Deep Learning through Spectral Perturbation and Filtering"],"prefix":"10.1109","author":[{"given":"Ce","family":"Feng","sequence":"first","affiliation":[{"name":"Lehigh University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nuo","family":"Xu","sequence":"additional","affiliation":[{"name":"Lehigh University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wujie","family":"Wen","sequence":"additional","affiliation":[{"name":"Lehigh University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Parv","family":"Venkitasubramaniam","sequence":"additional","affiliation":[{"name":"Lehigh University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caiwen","family":"Ding","sequence":"additional","affiliation":[{"name":"University of Connecticut"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2012.80"},{"key":"ref3","author":"Andrew","year":"2019","journal-title":"Differentially private learning with adaptive clipping"},{"key":"ref4","first-page":"383","article-title":"Private adaptive gradient methods for convex optimization","volume-title":"International Conference on Machine Learning","author":"Asi"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2014.56"},{"key":"ref6","article-title":"Privacy-preserving logistic regression","volume":"21","author":"Chaudhuri","year":"2008","journal-title":"Advances in neural information processing systems"},{"issue":"3","key":"ref7","article-title":"Differentially private empirical risk minimization","volume":"12","author":"Chaudhuri","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20586"},{"key":"ref9","article-title":"A downsampled variant of imagenet as an alternative to the cifar datasets","author":"Chrabaszcz","year":"2017","journal-title":"arXiv preprint arXiv:1707.08819"},{"key":"ref10","article-title":"Unlocking high-accuracy differentially private image classification through scale","author":"De","year":"2022","journal-title":"arXiv preprint arXiv:2204.13650"},{"key":"ref11","first-page":"395","article-title":"Circnn: Accelerating and compressing deep neural networks using block-circulant weight matrices","volume-title":"Proceedings of the 50th Annual IEEE\/ACM International Symposium on Microarchitecture, MICRO-50 \u201917","author":"Ding"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3289602.3293904"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2020.102701"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1561\/0400000042"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/1038020"},{"key":"ref16","article-title":"Differentially private federated learning: A client level perspective","author":"Geyer","year":"2017","journal-title":"arXiv preprint arXiv:1712.07557"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220076"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8342166"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.4208\/csiam-am.SO-2020-0005"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00502"},{"key":"ref25","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Artificial intelligence and statistics","author":"McMahan","year":"2017"},{"key":"ref26","article-title":"Learning differentially private recurrent language models","author":"McMahan","year":"2017","journal-title":"arXiv preprint arXiv:1710.06963"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2017.11"},{"key":"ref28","article-title":"R\u00e9nyi Differential Privacy of the Sampled Gaussian Mechanism","author":"Mironov","year":"2019","journal-title":"arXiv e-prints"},{"key":"ref29","article-title":"Improving deep learning with differential privacy using gradient encoding and denoising","author":"Nasr","year":"2020","journal-title":"arXiv preprint arXiv:2007.11524"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298904"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0129-8"},{"key":"ref32","article-title":"Semi-supervised knowledge transfer for deep learning from private training data","author":"Papernot","year":"2016","journal-title":"arXiv preprint arXiv:1610.05755"},{"key":"ref33","article-title":"Scalable private learning with pate","author":"Papernot","year":"2018","journal-title":"arXiv preprint arXiv:1802.08908"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17123"},{"key":"ref35","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref36","author":"Pichapati","year":"2019","journal-title":"Adaclip: Adaptive clipping for private sgd"},{"key":"ref37","first-page":"5301","article-title":"On the spectral bias of neural networks","volume-title":"International Conference on Machine Learning","author":"Rahaman"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807247"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1568318.1568324"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.29012\/jpc.v4i1.612"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref42","author":"Stevens","year":"2022","journal-title":"Backpropagation clipping for deep learning with differential privacy"},{"key":"ref43","first-page":"1379","article-title":"Efficient differentially private secure aggregation for federated learning via hardness of learning with errors","volume-title":"31st USENIX Security Symposium (USENIX Security 22)","author":"Stevens"},{"key":"ref44","article-title":"Differentially private learning needs better features (or much more data)","volume-title":"International Conference on Learning Representations","author":"Tramer"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3378679.3394533"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2988575"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36708-4_22"},{"key":"ref49","article-title":"Opacus: User-friendly differential privacy library in PyTorch","author":"Yousefpour","year":"2021","journal-title":"arXiv preprint arXiv:2109.12298"},{"key":"ref50","article-title":"Do not let privacy overbill utility: Gradient embedding perturbation for private learning","volume-title":"International Conference on Learning Representations","author":"Yu"},{"key":"ref51","first-page":"12208","article-title":"Large scale private learning via low-rank reparametrization","volume-title":"International Conference on Machine Learning","author":"Yu"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.14778\/2350229.2350253"}],"event":{"name":"2023 IEEE Symposium on Security and Privacy (SP)","location":"San Francisco, CA, USA","start":{"date-parts":[[2023,5,21]]},"end":{"date-parts":[[2023,5,25]]}},"container-title":["2023 IEEE Symposium on Security and Privacy (SP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10179215\/10179280\/10179457.pdf?arnumber=10179457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,20]],"date-time":"2024-07-20T05:16:56Z","timestamp":1721452616000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10179457\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/sp46215.2023.10179457","relation":{},"subject":[],"published":{"date-parts":[[2023,5]]}}}