{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:40:58Z","timestamp":1772120458450,"version":"3.50.1"},"reference-count":23,"publisher":"Privacy Enhancing Technologies Symposium Advisory Board","issue":"4","license":[{"start":{"date-parts":[[2021,7,23]],"date-time":"2021-07-23T00:00:00Z","timestamp":1626998400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/3.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>There is increasing awareness of the need to protect individual privacy in the training data used to develop machine learning models. Differential Privacy is a strong concept of protecting individuals. Na\u00efve Bayes is a popular machine learning algorithm, used as a baseline for many tasks. In this work, we have provided a differentially private Na\u00efve Bayes classifier that adds noise proportional to the <jats:italic>smooth sensitivity<\/jats:italic> of its parameters. We compare our results to Vaidya, Shafiq, Basu, and Hong [1] which scales noise to the global sensitivity of the parameters. Our experimental results on real-world datasets show that smooth sensitivity significantly improves accuracy while still guaranteeing <jats:italic>\u025b<\/jats:italic>-differential privacy.<\/jats:p>","DOI":"10.2478\/popets-2021-0077","type":"journal-article","created":{"date-parts":[[2021,7,24]],"date-time":"2021-07-24T23:17:53Z","timestamp":1627168673000},"page":"406-419","source":"Crossref","is-referenced-by-count":10,"title":["Differentially Private Na\u00efve Bayes Classifier Using Smooth Sensitivity"],"prefix":"10.56553","volume":"2021","author":[{"given":"Farzad","family":"Zafarani","sequence":"first","affiliation":[{"name":"Department of Computer Science , Purdue University , USA ."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chris","family":"Clifton","sequence":"additional","affiliation":[{"name":"Department of Computer Science , Purdue University , USA ."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"35752","published-online":{"date-parts":[[2021,7,23]]},"reference":[{"key":"2022051409230568547_j_popets-2021-0077_ref_001","doi-asserted-by":"crossref","unstructured":"[1] J. Vaidya, B. Shafiq, A. Basu, and Y. Hong, \u201cDifferentially private naive bayes classification,\u201d in 2013 IEEE\/WIC\/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT), vol. 1, pp. 571\u2013576, IEEE, 2013.10.1109\/WI-IAT.2013.80","DOI":"10.1109\/WI-IAT.2013.80"},{"key":"2022051409230568547_j_popets-2021-0077_ref_002","doi-asserted-by":"crossref","unstructured":"[2] C. Dwork, F. McSherry, K. Nissim, and A. Smith, \u201cCalibrating noise to sensitivity in private data analysis,\u201d in Theory of cryptography conference, pp. 265\u2013284, Springer, 2006.10.1007\/11681878_14","DOI":"10.1007\/11681878_14"},{"key":"2022051409230568547_j_popets-2021-0077_ref_003","doi-asserted-by":"crossref","unstructured":"[3] F. McSherry and K. Talwar, \u201cMechanism design via differential privacy.,\u201d in FOCS, vol. 7, pp. 94\u2013103, 2007.10.1109\/FOCS.2007.66","DOI":"10.1109\/FOCS.2007.66"},{"key":"2022051409230568547_j_popets-2021-0077_ref_004","doi-asserted-by":"crossref","unstructured":"[4] G. Jagannathan, K. Pillaipakkamnatt, and R. N. Wright, \u201cA practical differentially private random decision tree classifier,\u201d in 2009 IEEE International Conference on Data Mining Workshops, pp. 114\u2013121, IEEE, 2009.10.1109\/ICDMW.2009.93","DOI":"10.1109\/ICDMW.2009.93"},{"key":"2022051409230568547_j_popets-2021-0077_ref_005","unstructured":"[5] B. I. Rubinstein, P. L. Bartlett, L. Huang, and N. Taft, \u201cLearning in a large function space: Privacy-preserving mechanisms for svm learning,\u201d arXiv preprint arXiv:0911.5708, 2009."},{"key":"2022051409230568547_j_popets-2021-0077_ref_006","doi-asserted-by":"crossref","unstructured":"[6] M. Abadi, A. Chu, I. Goodfellow, H. B. McMahan, I. Mironov, K. Talwar, and L. Zhang, \u201cDeep learning with differential privacy,\u201d in Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, pp. 308\u2013318, ACM, 2016.10.1145\/2976749.2978318","DOI":"10.1145\/2976749.2978318"},{"key":"2022051409230568547_j_popets-2021-0077_ref_007","unstructured":"[7] K. Chaudhuri and C. Monteleoni, \u201cPrivacy-preserving logistic regression,\u201d in Advances in neural information processing systems, pp. 289\u2013296, 2009."},{"key":"2022051409230568547_j_popets-2021-0077_ref_008","doi-asserted-by":"crossref","unstructured":"[8] C. Dwork, V. Feldman, M. Hardt, T. Pitassi, O. Reignold, and A. Roth, \u201cGuilt-free data reuse,\u201d Communications of the ACM, vol. 80, pp. 86\u201393, Apr. 2017.10.1145\/3051088","DOI":"10.1145\/3051088"},{"key":"2022051409230568547_j_popets-2021-0077_ref_009","doi-asserted-by":"crossref","unstructured":"[9] K. Nissim, S. Raskhodnikova, and A. Smith, \u201cSmooth sensitivity and sampling in private data analysis,\u201d in Proceedings of the thirty-ninth annual ACM symposium on Theory of computing, pp. 75\u201384, ACM, 2007.10.1145\/1250790.1250803","DOI":"10.1145\/1250790.1250803"},{"key":"2022051409230568547_j_popets-2021-0077_ref_010","unstructured":"[10] M. Bun and T. Steinke, \u201cAverage-case averages: Private algorithms for smooth sensitivity and mean estimation,\u201d in Advances in Neural Information Processing Systems, pp. 181\u2013191, 2019."},{"key":"2022051409230568547_j_popets-2021-0077_ref_011","unstructured":"[11] T. M. Mitchell, \u201cMachine learning,\u201d 1997."},{"key":"2022051409230568547_j_popets-2021-0077_ref_012","doi-asserted-by":"crossref","unstructured":"[12] F. McSherry and I. Mironov, \u201cDifferentially private recommender systems: Building privacy into the netflix prize contenders,\u201d in Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 627\u2013636, ACM, 2009.10.1145\/1557019.1557090","DOI":"10.1145\/1557019.1557090"},{"key":"2022051409230568547_j_popets-2021-0077_ref_013","doi-asserted-by":"crossref","unstructured":"[13] C. Dwork and J. Lei, \u201cDifferential privacy and robust statistics.,\u201d in STOC, vol. 9, pp. 371\u2013380, 2009.10.1145\/1536414.1536466","DOI":"10.1145\/1536414.1536466"},{"key":"2022051409230568547_j_popets-2021-0077_ref_014","unstructured":"[14] D. Dua and C. Graff, \u201cUCI machine learning repository,\u201d 2017."},{"key":"2022051409230568547_j_popets-2021-0077_ref_015","unstructured":"[15] R. Bhatt and A. Dhall, \u201cSkin segmentation dataset,\u201d UCI Machine Learning Repository, 2010."},{"key":"2022051409230568547_j_popets-2021-0077_ref_016","doi-asserted-by":"crossref","unstructured":"[16] P. J. Phillips, H. Wechsler, J. Huang, and P. J. Rauss, \u201cThe feret database and evaluation procedure for face-recognition algorithms,\u201d Image and vision computing, vol. 16, no. 5, pp. 295\u2013306, 1998.10.1016\/S0262-8856(97)00070-X","DOI":"10.1016\/S0262-8856(97)00070-X"},{"key":"2022051409230568547_j_popets-2021-0077_ref_017","doi-asserted-by":"crossref","unstructured":"[17] T. Li, J. Li, Z. Liu, P. Li, and C. Jia, \u201cDifferentially private naive bayes learning over multiple data sources,\u201d Information Sciences, vol. 444, pp. 89\u2013104, 2018.10.1016\/j.ins.2018.02.056","DOI":"10.1016\/j.ins.2018.02.056"},{"key":"2022051409230568547_j_popets-2021-0077_ref_018","unstructured":"[18] E. Yilmaz, M. Al-Rubaie, and J. M. Chang, \u201cLocally differentially private naive bayes classification,\u201d arXiv preprint arXiv:1905.01039, 2019."},{"key":"2022051409230568547_j_popets-2021-0077_ref_019","unstructured":"[19] M. Kantarc\u0131oglu, J. Vaidya, and C. Clifton, \u201cPrivacy preserving naive bayes classifier for horizontally partitioned data,\u201d in IEEE ICDM workshop on privacy preserving data mining, pp. 3\u20139, 2003."},{"key":"2022051409230568547_j_popets-2021-0077_ref_020","doi-asserted-by":"crossref","unstructured":"[20] J. Vaidya and C. Clifton, \u201cPrivacy preserving naive bayes classifier for vertically partitioned data,\u201d in Proceedings of the 2004 SIAM International Conference on Data Mining, pp. 522\u2013526, SIAM, 2004.10.1137\/1.9781611972740.59","DOI":"10.1137\/1.9781611972740.59"},{"key":"2022051409230568547_j_popets-2021-0077_ref_021","doi-asserted-by":"crossref","unstructured":"[21] Z. Campbell, A. Bray, A. Ritz, and A. Groce, \u201cDifferentially private anova testing,\u201d in 2018 1st International Conference on Data Intelligence and Security (ICDIS), pp. 281\u2013285, IEEE, 2018.10.1109\/ICDIS.2018.00052","DOI":"10.1109\/ICDIS.2018.00052"},{"key":"2022051409230568547_j_popets-2021-0077_ref_022","doi-asserted-by":"crossref","unstructured":"[22] C. Task and C. Clifton, \u201cDifferentially private significance testing on paired-sample data,\u201d in Proceedings of the 2016 SIAM International Conference on Data Mining, pp. 153\u2013161, SIAM, 2016.10.1137\/1.9781611974348.18","DOI":"10.1137\/1.9781611974348.18"},{"key":"2022051409230568547_j_popets-2021-0077_ref_023","doi-asserted-by":"crossref","unstructured":"[23] B. Anandan and C. Clifton, \u201cDifferentially private feature selection for data mining,\u201d in Proceedings of the Fourth ACM International Workshop on Security and Privacy Analytics, pp. 43\u201353, ACM, 2018.10.1145\/3180445.3180452","DOI":"10.1145\/3180445.3180452"}],"container-title":["Proceedings on Privacy Enhancing Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.sciendo.com\/pdf\/10.2478\/popets-2021-0077","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,20]],"date-time":"2022-07-20T16:31:45Z","timestamp":1658334705000},"score":1,"resource":{"primary":{"URL":"https:\/\/petsymposium.org\/popets\/2021\/popets-2021-0077.php"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,23]]},"references-count":23,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2021,7,23]]},"published-print":{"date-parts":[[2021,10,1]]}},"alternative-id":["10.2478\/popets-2021-0077"],"URL":"https:\/\/doi.org\/10.2478\/popets-2021-0077","relation":{},"ISSN":["2299-0984"],"issn-type":[{"value":"2299-0984","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,23]]}}}