{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T02:09:10Z","timestamp":1740103750538,"version":"3.37.3"},"reference-count":37,"publisher":"Wiley","license":[{"start":{"date-parts":[[2020,12,16]],"date-time":"2020-12-16T00:00:00Z","timestamp":1608076800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2020JBM002","2018YFC0831703"],"award-info":[{"award-number":["2020JBM002","2018YFC0831703"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2020JBM002","2018YFC0831703"],"award-info":[{"award-number":["2020JBM002","2018YFC0831703"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Complexity"],"published-print":{"date-parts":[[2020,12,16]]},"abstract":"<jats:p>In this paper, we study the problem of protecting privacy in recommender systems. We focus on protecting the items rated by users and propose a novel privacy-preserving matrix factorization algorithm. In our algorithm, the user will submit a fake gradient to make the central server not able to distinguish which items are selected by the user. We make the Kullback\u2013Leibler distance between the real and fake gradient distributions to be small thus hard to be distinguished. Using theories and experiments, we show that our algorithm can be reduced to a time-delay SGD, which can be proved to have a good convergence so that the accuracy will not decline. Our algorithm achieves a good tradeoff between the privacy and accuracy.<\/jats:p>","DOI":"10.1155\/2020\/6683834","type":"journal-article","created":{"date-parts":[[2020,12,17]],"date-time":"2020-12-17T18:08:56Z","timestamp":1608228536000},"page":"1-10","source":"Crossref","is-referenced-by-count":1,"title":["A Smart Privacy-Preserving Learning Method by Fake Gradients to Protect Users Items in Recommender Systems"],"prefix":"10.1155","volume":"2020","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6446-9762","authenticated-orcid":true,"given":"Guixun","family":"Luo","sequence":"first","affiliation":[{"name":"School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6752-0794","authenticated-orcid":true,"given":"Zhiyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Key Laboratory of Communication and Information Systems, Beijing Municipal Commission of Education, Beijing Jiaotong University, Beijing 100044, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0217-3012","authenticated-orcid":true,"given":"Zhenjiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Beijing Jiaotong University, Beijing 100044, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2861-0316","authenticated-orcid":true,"given":"Yun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Key Laboratory of Communication and Information Systems, Beijing Municipal Commission of Education, Beijing Jiaotong University, Beijing 100044, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1890-8626","authenticated-orcid":true,"given":"Lifu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Key Laboratory of Communication and Information Systems, Beijing Municipal Commission of Education, Beijing Jiaotong University, Beijing 100044, China"}]}],"member":"311","reference":[{"key":"1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-018-0579-9"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2016.09.003"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.24846\/v29i2y202003"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.24846\/v28i2y201901"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.24818\/18423264\/53.2.19.05"},{"issue":"1","key":"6","first-page":"159","article-title":"Using data mining methods to solve classification problems in financial-banking institutions","volume":"54","author":"V. Oona","year":"2020","journal-title":"Economic Computation and Economic Cybernetics Studies and Research\/Academy of Economic Studies"},{"key":"7","article-title":"Implementation of artificial intelligence system and traditional system: a comparative study","volume":"66","author":"K. J. Ban","year":"2019","journal-title":"Journal of System and Management Sciences"},{"key":"8","article-title":"A blockchain and internet of things based architecture design for energy transaction","volume":"63","author":"S. Y. Y. Ji","year":"2020","journal-title":"Journal of System and Management Sciences"},{"key":"9","article-title":"A machine learning based method for customer behavior prediction","volume":"72","author":"S. H. L. Z. X. Li","year":"2019","journal-title":"Tehnicki vjesnik-Technical Gazette"},{"issue":"3","key":"10","article-title":"Applying the convolutional neural network deep learning technology to behavioural recognition in intelligent video","volume":"58","author":"N. Z. D. Qin","year":"2018","journal-title":"Tehnicki vjesnik-Technical Gazette"},{"issue":"5","key":"11","article-title":"You might also like: privacy risks of collaborative filtering","volume":"39","author":"J. A. Calandrino","year":"2012","journal-title":"Security & Privacy"},{"author":"F. Dan","key":"12","article-title":"Do you trust your recommendations? an exploration of security and privacy issues in recommender systems"},{"article-title":"Our data, ourselves: privacy via distributed noise generation","author":"C. Dwork","key":"13","doi-asserted-by":"crossref","DOI":"10.1007\/11761679_29"},{"key":"14","article-title":"Fast differentially private matrix factorization","volume":"9","author":"Z. Liu","year":"2015","journal-title":"Machine Learning"},{"author":"T. Zhu","key":"15","article-title":"Differential privacy for neighborhood-based collaborative filtering"},{"issue":"7","key":"16","doi-asserted-by":"crossref","DOI":"10.14778\/1988776.1988780","article-title":"Personalized social recommendations: accurate or private","volume":"4","author":"A. Machanavajjhala","year":"2011","journal-title":"Proceedings of the Vldb Endowment"},{"key":"17","first-page":"1","article-title":"Privacy enhanced matrix factorization for recommendation with local differential privacy","volume":"99","author":"H. Shin","year":"2018","journal-title":"IEEE Transactions on Knowledge & Data Engineering"},{"article-title":"Applying differential privacy to matrix factorization","author":"A. Berlioz","key":"18","doi-asserted-by":"crossref","DOI":"10.1145\/2792838.2800173"},{"author":"J. Hua","key":"19","article-title":"Differentially private matrix factorization"},{"author":"Y. Shen","key":"20","article-title":"Privacy-preserving personalized recommendation: an instance-based approach via differential privacy"},{"author":"Y. Shen","key":"21","article-title":"Epicrec: Towards practical differentially private framework for personalized recommendation"},{"author":"U. Erlingsson","key":"22","article-title":"Rappor:randomized aggregatable privacy-preserving ordinal response"},{"key":"23"},{"key":"24","article-title":"Collecting and analyzing data from smart device users with local differential privacy","volume":"16","author":"T. T. Nguyen","year":"2016","journal-title":"Computer Science Databases"},{"issue":"2","key":"25","first-page":"51","article-title":"Boosting and differential privacy","volume":"26","author":"C. Dwork","year":"2010","journal-title":"Foundations of Computer Science Annual Symposium on"},{"author":"M. Abadi","key":"26","article-title":"Deep learning with differential privacy"},{"volume-title":"Elements of Information Theory","year":"2003","author":"T. M. Cover","key":"27"},{"key":"28","first-page":"43","article-title":"Differential privacy as a mutual information constraint","volume":"28","author":"P. Cuff","year":"2016","journal-title":"Computer and Communications Security"},{"issue":"8","key":"29","first-page":"265","article-title":"Calibrating noise to sensitivity in private data analysis","volume":"3876","author":"C. Dwork","year":"2012","journal-title":"Lecture Notes in Computer Ence"},{"key":"30","first-page":"1","article-title":"A hitting time analysis of stochastic gradient langevin dynamics","volume":"65","author":"Y. Zhang","year":"2017","journal-title":"Proceedings of Machine Learning Research"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1965.10480775"},{"author":"X. Lian","key":"32","article-title":"Asynchronous parallel stochastic gradient for nonconvex optimization"},{"key":"33","article-title":"Stochastic gradient descent escapes saddle points efficiently","volume":"31","author":"C. Jin","year":"2019","journal-title":"arXiv: Learning"},{"key":"34","doi-asserted-by":"publisher","DOI":"10.1145\/2827872"},{"volume-title":"Differentially private federated learning: a client level perspective","year":"2017","author":"R. C. Geyer","key":"35"},{"issue":"4","key":"36","first-page":"671","article-title":"Privacy-preserving collaborative filtering using randomized response","volume":"21","author":"H. Kikuchi","year":"2012","journal-title":"Journal of Information Processing"},{"author":"Y. Xin","key":"37","article-title":"Controlling privacy in recommender systems"}],"container-title":["Complexity"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2020\/6683834.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2020\/6683834.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2020\/6683834.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,17]],"date-time":"2020-12-17T18:09:08Z","timestamp":1608228548000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/complexity\/2020\/6683834\/"}},"subtitle":[],"editor":[{"given":"Abd E.I.-Baset","family":"Hassanien","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2020,12,16]]},"references-count":37,"alternative-id":["6683834","6683834"],"URL":"https:\/\/doi.org\/10.1155\/2020\/6683834","relation":{},"ISSN":["1099-0526","1076-2787"],"issn-type":[{"type":"electronic","value":"1099-0526"},{"type":"print","value":"1076-2787"}],"subject":[],"published":{"date-parts":[[2020,12,16]]}}}