{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T21:37:00Z","timestamp":1784065020731,"version":"3.55.0"},"reference-count":63,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T00:00:00Z","timestamp":1635206400000},"content-version":"vor","delay-in-days":298,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key R&D Program of China","award":["2018YFC1604000"],"award-info":[{"award-number":["2018YFC1604000"]}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>Artificial Intelligence has been widely applied today, and the subsequent privacy leakage problems have also been paid attention to. Attacks such as model inference attacks on deep neural networks can easily extract user information from neural networks. Therefore, it is necessary to protect privacy in deep learning. Differential privacy, as a popular topic in privacy\u2010preserving in recent years, which provides rigorous privacy guarantee, can also be used to preserve privacy in deep learning. Although many articles have proposed different methods to combine differential privacy and deep learning, there are no comprehensive papers to analyze and compare the differences and connections between these technologies. For this purpose, this paper is proposed to compare different differential private methods in deep learning. We comparatively analyze and classify several deep learning models under differential privacy. Meanwhile, we also pay attention to the application of differential privacy in Generative Adversarial Networks (GANs), comparing and analyzing these models. Finally, we summarize the application of differential privacy in deep neural networks.<\/jats:p>","DOI":"10.1155\/2021\/4244040","type":"journal-article","created":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T22:35:18Z","timestamp":1635287718000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Analysis of Application Examples of Differential Privacy in Deep Learning"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4880-381X","authenticated-orcid":false,"given":"Zhidong","family":"Shen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2021,10,26]]},"reference":[{"key":"e_1_2_11_1_2","doi-asserted-by":"crossref","unstructured":"HeK. ZhangX. RenS. andSunJ. Delving deep into rectifiers: surpassing human-level performance on imagenet classification Proceedings of the 2015 IEEE International Conference on Computer Vision ICCV 2015 December 2015 Santiago Chile 1026\u20131034 https:\/\/doi.org\/10.1109\/iccv.2015.123 2-s2.0-84973911419.","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_2_11_2_2","doi-asserted-by":"crossref","unstructured":"MalmasiS.andZampieriM. Detecting hate speech in social media Proceedings of the Recent Advances in Natural Language Processing (RANLP) September 2017 Varna Bulgaria 467\u2013472 https:\/\/doi.org\/10.26615\/978-954-452-049-6_062.","DOI":"10.26615\/978-954-452-049-6_062"},{"key":"e_1_2_11_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dt.2019.12.006"},{"key":"e_1_2_11_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2020.101951"},{"key":"e_1_2_11_5_2","unstructured":"HarderF. BauerM. andParkM. Interpretable and differentially private predictions 2019 https:\/\/arxiv.org\/pdf\/1906.02004.pdf."},{"key":"e_1_2_11_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-016-2248-1"},{"key":"e_1_2_11_7_2","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/6693730"},{"key":"e_1_2_11_8_2","doi-asserted-by":"crossref","unstructured":"ShokriR. StronatiM. SongC. andShmatikovV. Membership inference attacks against machine learning models Proceedings of the 2017 IEEE Symposium on Security and Privacy SP 2017 May 2017 San Jose CA USA 3\u201318 https:\/\/doi.org\/10.1109\/sp.2017.41 2-s2.0-85024479480.","DOI":"10.1109\/SP.2017.41"},{"key":"e_1_2_11_9_2","doi-asserted-by":"crossref","unstructured":"FredriksonM. JhaS. andRistenpartT. Model inversion attacks that exploit confidence information and basic countermeasures Proceedings of the ACM Conference on Computer and Communications Security 2015 October 2015 Denver CO USA 1322\u20131333 https:\/\/doi.org\/10.1145\/2810103.2813677 2-s2.0-84954097669.","DOI":"10.1145\/2810103.2813677"},{"key":"e_1_2_11_10_2","doi-asserted-by":"crossref","unstructured":"WangR. LiY. WangX. TangH. andZhouX. Learning Your Identity and Disease from Research Papers: Information Leaks in Genome Wide Association Study Proceedings of the 16th ACM Conference on Computer and Communications Security November 2009 Chicago IL USA.","DOI":"10.1145\/1653662.1653726"},{"key":"e_1_2_11_11_2","unstructured":"LeFevreI. K. DeWittD. andRamakrishnanR. Efficient full-domain kanonymity Proceedings of the ACM SIGMOD International Conference on Management of Data June 2005 Baltimore MD USA."},{"key":"e_1_2_11_12_2","doi-asserted-by":"publisher","DOI":"10.13328\/j.cnki.jos.004808"},{"key":"e_1_2_11_13_2","doi-asserted-by":"crossref","unstructured":"MachanavajjhalaA. KiferD. GehrkeJ. andVenkitasubramaniamM. l-Diversity: Privacy Beyond Discovery 2007 1 https:\/\/doi.org\/10.1145\/1217299.1217302 2-s2.0-34248181923.","DOI":"10.1145\/1217299.1217302"},{"key":"e_1_2_11_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21554-4_8"},{"key":"e_1_2_11_15_2","first-page":"1","article-title":"The connection between cryptography and differential privacy: a survey","volume":"14","author":"Huang W.","year":"2020","journal-title":"Computer Security and Reliability"},{"key":"e_1_2_11_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2017.2697856"},{"key":"e_1_2_11_17_2","unstructured":"BalleB.andWangY. X. Improving the Gaussian mechanism for differential privacy: analytical calibration and optimal denoising 1 Proceedings of the 35th International Conference on Machine Learning (ICML 2018) July 2018 Stockholm Sweden 678\u2013692."},{"key":"e_1_2_11_18_2","first-page":"1069","article-title":"Differentially private empirical risk minimization","volume":"12","author":"Chaudhuri K.","year":"2011","journal-title":"Journal of Machine Learning Research: JMLR"},{"key":"e_1_2_11_19_2","doi-asserted-by":"crossref","unstructured":"ChaudhuriK.andMonteleoniC. Privacy-preserving logistic regression Proceedings of the 21st International Conference on Neural Information Processing December 2008 Vancouver Canada 289\u2013296 https:\/\/doi.org\/10.12720\/jait.6.3.88-95.","DOI":"10.12720\/jait.6.3.88-95"},{"key":"e_1_2_11_20_2","doi-asserted-by":"publisher","DOI":"10.14778\/2350229.2350253"},{"key":"e_1_2_11_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2019.2952146"},{"key":"e_1_2_11_22_2","unstructured":"NasrM. ShokriR. andHoumansadrA. Comprehensive privacy analysis of deep learning Proceedings of the 2019 IEEE Symposium on Security and Privacy (SP) May 2019 San Francisco CA USA 1\u201315."},{"key":"e_1_2_11_23_2","doi-asserted-by":"crossref","unstructured":"AbadiM. McMahanH. B. ChuA. MironovI. ZhangL. GoodfellowI. andTalwarK. Deep learning with differential privacy Proceedings of the ACM Conference on Computer and Communications Security October 2016 Vienna Austria 308\u2013318 https:\/\/doi.org\/10.1145\/2976749.2978318 2-s2.0-84995527907.","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_2_11_24_2","doi-asserted-by":"crossref","unstructured":"SongS. ChaudhuriK. andSarwateA. D. Stochastic gradient descent with differentially private updates Proceedings of the 2013 IEEE Global Conference on Signal and Information Processing December 2013 Austin TX USA 245\u2013248 https:\/\/doi.org\/10.1109\/globalsip.2013.6736861 2-s2.0-84897680504.","DOI":"10.1109\/GlobalSIP.2013.6736861"},{"key":"e_1_2_11_25_2","doi-asserted-by":"publisher","DOI":"10.1162\/99608f92.cfc5dd25"},{"key":"e_1_2_11_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00779-021-01545-0"},{"key":"e_1_2_11_27_2","doi-asserted-by":"crossref","unstructured":"DworkC. Differential privacy Proceedings of the 33rd international conference on Automata Languages and Programming July 2006 Venice Italy 1\u201312 https:\/\/doi.org\/10.1007\/11787006_1 2-s2.0-33746335051.","DOI":"10.1007\/11787006_1"},{"key":"e_1_2_11_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/11761679_29"},{"key":"e_1_2_11_29_2","doi-asserted-by":"crossref","unstructured":"McsherryF.andTalwarK. Mechanism design via differential privacy Proceedings of the Annual IEEE Symposium on Foundations of Computer Science 2007 Providence RI USA.","DOI":"10.1109\/FOCS.2007.66"},{"key":"e_1_2_11_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/1810891.1810916"},{"key":"e_1_2_11_31_2","doi-asserted-by":"publisher","DOI":"10.1561\/0400000042"},{"key":"e_1_2_11_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/1866739.1866758"},{"key":"e_1_2_11_33_2","doi-asserted-by":"publisher","DOI":"10.1561\/9781601982957"},{"key":"e_1_2_11_34_2","doi-asserted-by":"crossref","unstructured":"PapernotN. McDanielP. SinhaA. andWellmanM. P. SoK: security and privacy in machine learning Proceedings of the 3rd IEEE European Symposium on Security and Privacy April 2018 London UK 399\u2013414 https:\/\/doi.org\/10.1109\/eurosp.2018.00035 2-s2.0-85050721582.","DOI":"10.1109\/EuroSP.2018.00035"},{"key":"e_1_2_11_35_2","unstructured":"Tram\u00e8rF. ZhangF. JuelsA. ReiterM. K. andRistenpartT. Stealing machine learning models via prediction APIs Proceedings of the 25th USENIX Security Symposium USENIX Security August 2016 Austin TX USA 601\u2013618."},{"key":"e_1_2_11_36_2","unstructured":"YangC. WuQ. LiH. andChenY. Generative poisoning attack method against neural networks 2017 http:\/\/arxiv.org\/abs\/1703.01340."},{"key":"e_1_2_11_37_2","unstructured":"McMahanH. B. AndrewG. ErlingssonU. ChienS. MironovI. PapernotN. andKairouzP. A general approach to adding differential privacy to iterative training procedures 2018 http:\/\/arxiv.org\/abs\/1812.06210."},{"key":"e_1_2_11_38_2","doi-asserted-by":"crossref","unstructured":"AbadiM. Erlingsson\u00da. GoodfellowI. McMahanH. B. MironovI. PapernotN. TalwarK. andZhangL. On the protection of private information in machine learning systems: two recent approches Proceedings of the 2017 IEEE 30th Computer Security Foundations Symposium August 2017 Santa Barbara CA USA 1\u20136 https:\/\/doi.org\/10.1109\/csf.2017.10 2-s2.0-85033784607.","DOI":"10.1109\/CSF.2017.10"},{"key":"e_1_2_11_39_2","doi-asserted-by":"crossref","unstructured":"DworkC. RothblumG. N. andVadhanS. Boosting and differential privacy Proceedings of the Annual Symposium on Foundations of Computer Science FOCS 2010 October 2010 Las Vegas NV USA 51\u201360 https:\/\/doi.org\/10.1109\/focs.2010.12 2-s2.0-78751522594.","DOI":"10.1109\/FOCS.2010.12"},{"key":"e_1_2_11_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5404-1"},{"key":"e_1_2_11_41_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"e_1_2_11_42_2","doi-asserted-by":"crossref","unstructured":"YuL. LiuL. PuC. GursoyM. E. andTruexS. Differentially private model publishing for deep learning Proceedings of the 2019 IEEE Symposium on Security and Privacy (SP) May 2019 San Francisco CA USA 332\u2013349 https:\/\/doi.org\/10.1109\/sp.2019.00019 2-s2.0-85071317979.","DOI":"10.1109\/SP.2019.00019"},{"key":"e_1_2_11_43_2","unstructured":"DworkC.andRothblumG. N. Concentrated differential privacy 2016 1\u201328 http:\/\/arxiv.org\/abs\/1603.01887."},{"key":"e_1_2_11_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-53641-4_24"},{"key":"e_1_2_11_45_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-019-01440-w"},{"key":"e_1_2_11_46_2","doi-asserted-by":"crossref","unstructured":"PhanN. WuX. HuH. andDouD. Adaptive laplace mechanism: differential privacy preservation in deep learning Proceedings of the 2017 IEEE International Conference on Data Mining (ICDM) November 2017 New Orleans LA USA 2278\u20132324 https:\/\/doi.org\/10.1109\/icdm.2017.48 2-s2.0-85043981824.","DOI":"10.1109\/ICDM.2017.48"},{"key":"e_1_2_11_47_2","doi-asserted-by":"crossref","unstructured":"ShokriR.andShmatikovV. Privacy-preserving deep learning Proceedings of the 2015 53rd Annual Allerton Conference on Communication Control and Computing September 2015 Monticello IL USA 909\u2013910 https:\/\/doi.org\/10.1109\/ALLERTON.2015.7447103 2-s2.0-84969765401.","DOI":"10.1109\/ALLERTON.2015.7447103"},{"key":"e_1_2_11_48_2","doi-asserted-by":"crossref","unstructured":"DworkC.andLeiJ. Differential privacy and robust statistics Proceedings of the 41st Annual ACM Symposium on Theory of Computing May-June 2009 Bethesda MD USA 371\u2013380 https:\/\/doi.org\/10.1145\/1536414.1536466 2-s2.0-70350682013.","DOI":"10.1145\/1536414.1536466"},{"key":"e_1_2_11_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_11_50_2","doi-asserted-by":"crossref","unstructured":"LeeH. GrosseR. RanganathR. andNgA. Y. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations Proceedings of the 26th International Conference on Machine Learning (ICML 2009) June 2009 Montreal Canada 609\u2013616 https:\/\/doi.org\/10.1145\/1553374.1553453.","DOI":"10.1145\/1553374.1553453"},{"key":"e_1_2_11_51_2","doi-asserted-by":"crossref","unstructured":"PhanN. WangY. WuX. andDouD. Differential privacy preservation for deep auto-encoders: an application of human behavior prediction Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence February 2016 Phoenix AZ USA.","DOI":"10.1609\/aaai.v30i1.10165"},{"key":"e_1_2_11_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-017-5656-2"},{"key":"e_1_2_11_53_2","doi-asserted-by":"crossref","unstructured":"LiX. DuN. LiH. LiK. GaoJ. andZhangA. A deep learning approach to link prediction in dynamic networks 1 Proceedings of the 2014 SIAM International Conference on Data Mining April 2014 Philadelphia PA USA 289\u2013297 https:\/\/doi.org\/10.1137\/1.9781611973440.33 2-s2.0-84954101093.","DOI":"10.1137\/1.9781611973440.33"},{"key":"e_1_2_11_54_2","unstructured":"PapernotN. GoodfellowI. AbadiM. TalwarK. andErlingsson\u00da. Semi-supervised knowledge transfer for deep learning from private training data Proceedings of the 5th International Conference on Learning Representations ICLR 2017 April 2019) Toulon France 1\u201316."},{"key":"e_1_2_11_55_2","doi-asserted-by":"publisher","DOI":"10.3156\/jsoft.29.5_177_2"},{"key":"e_1_2_11_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134012"},{"key":"e_1_2_11_57_2","unstructured":"XieL. LinK. WangS. WangF. andZhouJ. Differentially private generative adversarial network 2018 http:\/\/arxiv.org\/abs\/1802.06739."},{"key":"e_1_2_11_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/tifs.2019.2897874"},{"key":"e_1_2_11_59_2","doi-asserted-by":"publisher","DOI":"10.1161\/circoutcomes.118.005122"},{"key":"e_1_2_11_60_2","unstructured":"ArjovskyM. ChintalaS. BottouL. andGANW. Wasserstein GAN 2017 http:\/\/arxiv.org\/abs\/1701.07875."},{"key":"e_1_2_11_61_2","first-page":"419","volume-title":"Hum. Mach. Hear.","author":"Hinton G.","year":"2018"},{"key":"e_1_2_11_62_2","doi-asserted-by":"crossref","unstructured":"HeK. ZhangX. RenS. andSunJ. Deep residual learning for image recognition Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition December 2016 Las Vegas NV USA 770\u2013778 https:\/\/doi.org\/10.1109\/cvpr.2016.90 2-s2.0-84986274465.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_11_63_2","unstructured":"IoffeS.andSzegedyC. Batch normalization: accelerating deep network training by reducing internal covariate shift 1 Proceedings of the 32nd International Conference on Machine Learning (ICML 2015) July 2015 Lille France 448\u2013456."}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/4244040.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/4244040.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/4244040","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T11:20:44Z","timestamp":1722943244000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/4244040"}},"subtitle":[],"editor":[{"given":"Elpida","family":"Keravnou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":63,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/4244040"],"URL":"https:\/\/doi.org\/10.1155\/2021\/4244040","archive":["Portico"],"relation":{},"ISSN":["1687-5265","1687-5273"],"issn-type":[{"value":"1687-5265","type":"print"},{"value":"1687-5273","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2021-05-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-10-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"4244040"}}