{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T15:24:26Z","timestamp":1788449066788,"version":"build-2803163510"},"reference-count":62,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-009"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-001"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1109\/sp46214.2022.9833648","type":"proceedings-article","created":{"date-parts":[[2022,7,27]],"date-time":"2022-07-27T15:28:05Z","timestamp":1658935685000},"page":"2487-2501","source":"Crossref","is-referenced-by-count":23,"title":["Sphinx: Enabling Privacy-Preserving Online Learning over the Cloud"],"prefix":"10.1109","author":[{"given":"Han","family":"Tian","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaoliang","family":"Zeng","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenghang","family":"Ren","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Chai","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junxue","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Yang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2478\/popets-2019-0035"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2457317.2457343"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243760"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3363207"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2010.12"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3339819"},{"key":"ref58","article-title":"Inverting gradients-how easy is it to break privacy in federated learning?","author":"geiping","year":"2020","journal-title":"arXiv preprint arXiv 2003 14053"},{"key":"ref53","volume":"1","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref52","article-title":"Federated singular vector decomposition","author":"chai","year":"2021","journal-title":"arXiv preprint arXiv 2105 08925"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.12"},{"key":"ref55","article-title":"Microsoft SEAL (release 3.6)","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00011"},{"key":"ref54","first-page":"409","article-title":"Homomorphic encryption for arithmetic of approximate numbers","author":"cheon","year":"2017","journal-title":"International Conference on the Theory and Application of Cryptology and Information Security"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.48"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10165"},{"key":"ref19","first-page":"5213","article-title":"Practical and private (deep) learning without sampling or shuffling","volume":"139","author":"kairouz","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning ser Proceedings of Machine Learning Research"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/99608f92.cfc5dd25"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63076-8_16"},{"key":"ref50","article-title":"Secure federated matrix factorization","author":"chai","year":"2020","journal-title":"IEEE Intelligent Systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-24271-8_2"},{"key":"ref45","article-title":"Distributed learning without distress: Privacy-preserving empirical risk minimization","author":"jayaraman","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref48","article-title":"Poseidon: Privacy-preserving federated neural network learning","author":"sav","year":"2022"},{"key":"ref47","first-page":"1","article-title":"A hybrid approach to privacy-preserving federated learning","author":"truex","year":"2019","journal-title":"Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security"},{"key":"ref42","article-title":"Federated learning: Strategies for improving communication efficiency","author":"kone?n\u00fd","year":"2016","journal-title":"arXiv preprint arXiv 1610 05492"},{"key":"ref41","article-title":"Practical secure aggregation for federated learning on user-held data","author":"bonawitz","year":"2016","journal-title":"arXiv preprint arXiv 1611 04482"},{"key":"ref44","article-title":"Protection against reconstruction and its applications in private federated learning","author":"bhowmick","year":"2018","journal-title":"arXiv preprint arXiv 1812 09832"},{"key":"ref43","first-page":"1333","article-title":"Privacy-preserving deep learning via additively homomorphic encryption","volume":"13","author":"aono","year":"2017","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"ref49","first-page":"1808","article-title":"Secure efficient federated knn for recommendation systems","author":"liu","year":"2020","journal-title":"The International Conference on Natural Computation Fuzzy Systems and Knowledge Discovery"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2013.30"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2196\/medinform.8805"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btv563"},{"key":"ref4","article-title":"Slalom: Fast, verifiable and private execution of neural networks in trusted hardware","author":"tramer","year":"2018","journal-title":"arXiv preprint arXiv 1806 03287"},{"key":"ref3","first-page":"1651","article-title":"{GAZELLE}: A low latency framework for secure neural network inference","author":"juvekar","year":"2018","journal-title":"27th USENIX Security Symposium ( USENIX Security 18)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3267973.3267974"},{"key":"ref5","first-page":"2505","article-title":"Delphi: A cryptographic inference service for neural networks","author":"mishra","year":"2020","journal-title":"29th USENIX Security Symposium USENIX Security 20"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813687"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2660267.2660348"},{"key":"ref34","article-title":"Privacy loss in apple’s implementation of differential privacy on macos 10.12","author":"tang","year":"2017","journal-title":"arXiv preprint arXiv 1709 02505"},{"key":"ref37","article-title":"Trident: Efficient 4pc framework for privacy preserving machine learning","author":"rachuri","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat4807"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.14778\/2350229.2350253"},{"key":"ref30","first-page":"486","article-title":"Our data, ourselves: Privacy via distributed noise generation","author":"dwork","year":"2006","journal-title":"Annual International Conference on the Theory and Applications of Cryptographic Techniques"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63076-8_2"},{"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 05729"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134056"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2015.23113"},{"key":"ref38","article-title":"Falcon: Honest-majority maliciously secure framework for private deep learning","author":"wagh","year":"2020","journal-title":"Proceedings on Privacy Enhancing Technologies"},{"key":"ref24","first-page":"201","article-title":"Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy","author":"gilad-bachrach","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2478\/popets-2020-0036"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1145\/3338469.3358944","article-title":"ngraphhe2: A high-throughput framework for neural network inference on encrypted data","author":"boemer","year":"2019","journal-title":"Proceedings of the 7th ACM Workshop on Encrypted Computing & Applied Homomorphic Cryptography"},{"key":"ref25","article-title":"Cryptodl: Deep neural networks over encrypted data","author":"hesamifard","year":"2017","journal-title":"arXiv preprint arXiv 1711 05847"},{"key":"ref20","first-page":"1895","article-title":"Evaluating differentially private machine learning in practice","author":"jayaraman","year":"2019","journal-title":"28th USENIX Security Symposium ( USENIX Security 19)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1515\/popets-2018-0024"},{"key":"ref21","article-title":"idlg: Improved deep leakage from gradients","author":"zhao","year":"2020","journal-title":"arXiv preprint arXiv 2001 02466"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2020.24202"},{"key":"ref27","first-page":"1501","article-title":"{XONN}: Xnor-based oblivious deep neural network inference","author":"riazi","year":"2019","journal-title":"28th USENIX Security Symposium ( USENIX Security 19)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/3910250"},{"key":"ref60","article-title":"R\\’enyi differential privacy of the sampled gaussian mechanism","author":"mironov","year":"2019","journal-title":"arXiv preprint arXiv 1908 11444"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1186\/s12920-020-0719-9"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3188745.3188946"}],"event":{"name":"2022 IEEE Symposium on Security and Privacy (SP)","location":"San Francisco, CA, USA","start":{"date-parts":[[2022,5,22]]},"end":{"date-parts":[[2022,5,26]]}},"container-title":["2022 IEEE Symposium on Security and Privacy (SP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9833550\/9833558\/09833648.pdf?arnumber=9833648","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,8]],"date-time":"2023-11-08T18:04:13Z","timestamp":1699466653000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9833648\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/sp46214.2022.9833648","relation":{},"subject":[],"published":{"date-parts":[[2022,5]]}}}