{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T12:48:07Z","timestamp":1773060487839,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T00:00:00Z","timestamp":1664150400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T00:00:00Z","timestamp":1664150400000},"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":[[2022,9,26]]},"DOI":"10.1109\/mmsp55362.2022.9950001","type":"proceedings-article","created":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T21:39:16Z","timestamp":1669153156000},"page":"01-06","source":"Crossref","is-referenced-by-count":3,"title":["Privacy-Preserving Student Learning with Differentially Private Data-Free Distillation"],"prefix":"10.1109","author":[{"given":"Bochao","family":"Liu","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China,100095"}]},{"given":"Jianghu","family":"Lu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China,100095"}]},{"given":"Pengju","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China,100095"}]},{"given":"Junjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Communication and Information Engineering, Shanghai University,Shanghai,China,200444"}]},{"given":"Dan","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Communication and Information Engineering, Shanghai University,Shanghai,China,200444"}]},{"given":"Zhenxing","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University,Shanghai,China,200433"}]},{"given":"Shiming","family":"Ge","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China,100095"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref11","first-page":"27131","article-title":"Deep learning with label differential privacy","author":"ghazi","year":"2021","journal-title":"NeurIPS"},{"key":"ref12","first-page":"6934","article-title":"Antipodes of label differential privacy: Pate and alibi","author":"malek esmaeili","year":"2021","journal-title":"NeurIPS"},{"key":"ref13","article-title":"Label private deep learning training based on secure multiparty computation and differential privacy","author":"yuan","year":"0","journal-title":"NeurIPS workshop"},{"key":"ref14","first-page":"7055","article-title":"Label differential privacy via clustering","author":"esfandiari","year":"2022","journal-title":"AISTATS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00361"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20613"},{"key":"ref17","first-page":"155","article-title":"Sample complexity bounds for differentially private learning","author":"chaudhuri","year":"2011","journal-title":"COLT"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1965.10480775"},{"key":"ref19","author":"lecun","year":"2010","journal-title":"MNIST Handwritten Digit Database"},{"key":"ref28","first-page":"12480","article-title":"Don't generate me: Training differentially private generative models with sinkhorn divergence","author":"cao","year":"2021","journal-title":"NeurIPS"},{"key":"ref4","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"ICLRE"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3484579"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","article-title":"Semi-supervised knowledge transfer for deep learning from private training data","author":"papernot","year":"2017","journal-title":"ICLRE"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00033"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813677"},{"key":"ref2","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/11681878_14"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref20","author":"xiao","year":"2017","journal-title":"Fashion-mnist a novel image dataset for benchmarking machine learning algorithms"},{"key":"ref22","author":"xie","year":"2018","journal-title":"Differentially private generative adversarial network"},{"key":"ref21","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009","journal-title":"Tech Rep"},{"key":"ref24","first-page":"12:673","article-title":"Gs-wgan: A gradient-sanitized approach for learning differentially private generators","author":"chen","year":"2020","journal-title":"NeurIPS"},{"key":"ref23","article-title":"Pate-gan: Generating synthetic data with differential privacy guarantees","author":"jordon","year":"2019","journal-title":"ICLRE"},{"key":"ref26","first-page":"1819","article-title":"Dp-merf: Differentially private mean embeddings with random features for practical privacy preserving data generation","author":"harder","year":"2021","journal-title":"AISTATS"},{"key":"ref25","author":"long","year":"2019","journal-title":"Scalable differentially private generative student model via PATE"}],"event":{"name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","location":"Shanghai, China","start":{"date-parts":[[2022,9,26]]},"end":{"date-parts":[[2022,9,28]]}},"container-title":["2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9948698\/9948704\/09950001.pdf?arnumber=9950001","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:54:04Z","timestamp":1670874844000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9950001\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,26]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/mmsp55362.2022.9950001","relation":{},"subject":[],"published":{"date-parts":[[2022,9,26]]}}}