{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:02:15Z","timestamp":1757617335389,"version":"3.44.0"},"reference-count":23,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"9","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Fundamentals"],"published-print":{"date-parts":[[2025,9,1]]},"DOI":"10.1587\/transfun.2024eap1123","type":"journal-article","created":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T17:11:35Z","timestamp":1740417095000},"page":"1281-1290","source":"Crossref","is-referenced-by-count":0,"title":["A Composition Theorem via &lt;i&gt;f&lt;\/i&gt;-Divergence Differential Privacy"],"prefix":"10.1587","volume":"E108.A","author":[{"given":"Shota","family":"SAITO","sequence":"first","affiliation":[{"name":"Faculty of Informatics, Gunma University"}]},{"given":"Koji","family":"CHIDA","sequence":"additional","affiliation":[{"name":"Faculty of Informatics, Gunma University"}]},{"given":"Osamu","family":"TAKAKI","sequence":"additional","affiliation":[{"name":"Faculty of Informatics, Gunma University"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] M. Abadi, A. Chu, I. Goodfellow, H.B. McMahan, I. Mironov, K. Talwar, and L. Zhang, \u201cDeep learning with differential privacy,\u201d 2016 ACM SIGSAC Conference on Computer and Communications Security (CCS\u201916), pp.308-318, 2016. 10.1145\/2976749.2978318","DOI":"10.1145\/2976749.2978318"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] S.M. Ali and S.D. Silvey, \u201cA general class of coefficients of divergence of one distribution from another,\u201d Journal of the Royal Statistical Society. Series B (Methodological), vol.28, no.1, pp.131-142, 1966. 10.1111\/j.2517-6161.1966.tb00626.x","DOI":"10.1111\/j.2517-6161.1966.tb00626.x"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] S. Asoodeh, J. Liao, F.P. Calmon, O. Kosut, and L. Sankar, \u201cA better bound gives a hundred rounds: Enhanced privacy guarantees via <i>f<\/i>-divergences,\u201d 2020 IEEE International Symposium on Information Theory (ISIT), Los Angeles, CA, USA, pp.920-925, 2020. 10.1109\/isit44484.2020.9174015","DOI":"10.1109\/ISIT44484.2020.9174015"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] S. Asoodeh, J. Liao, F.P. Calmon, O. Kosut, and L. Sankar, \u201cThree variants of differential privacy: Lossless conversion and applications,\u201d IEEE J. Sel. Areas Inf. Theory, vol.2, no.1, pp.208-222, 2021. 10.1109\/jsait.2021.3054692","DOI":"10.1109\/JSAIT.2021.3054692"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] S. Asoodeh, M. Aliakbarpour, and F.P. Calmon, \u201cLocal differential privacy is equivalent to contraction of an <i>f<\/i>-divergence,\u201d 2021 IEEE International Symposium on Information Theory (ISIT), Melbourne, Australia, pp.545-550, 2021. 10.1109\/isit45174.2021.9517999","DOI":"10.1109\/ISIT45174.2021.9517999"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] G. Barthe and F. Olmedo, \u201cBeyond differential privacy: Composition theorems and relational logic for <i>f<\/i>-divergences between probabilistic programs,\u201d ICALP 2013, Lecture Notes in Computer Science, vol.7966, pp.49-60, Springer, Berlin, Heidelberg, 2013. 10.1007\/978-3-642-39212-2_8","DOI":"10.1007\/978-3-642-39212-2_8"},{"key":"7","unstructured":"[7] K. Chaudhuri, J. Imola, and A. Machanavajjhala, \u201cCapacity bounded differential privacy,\u201d Proc. 33rd International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, Article 312, pp.3474-3483, 2019."},{"key":"8","unstructured":"[8] X. Chen, A. Guntuboyina, and Y. Zhang, \u201cOn Bayes risk lower bounds,\u201d Journal of Machine Learning Research, vol.17, no.1, pp.1-58, 2016."},{"key":"9","unstructured":"[9] T.M. Cover and J.A. Thomas, Elements of Information Theory, 2nd ed., Wiley-Interscience, 2006."},{"key":"10","unstructured":"[10] I. Csisz\u00e1r, \u201cInformation-type measures of difference of probability distributions and indirect observation,\u201d Studia Scientiarum Mathematicarum Hungarica, pp.229-318, 1967."},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] C. Dwork, F. McSherry, K. Nissim, and A. Smith, \u201cCalibrating noise to sensitivity in private data analysis,\u201d TCC 2006, Lecture Notes in Computer Science, vol.3876, pp.265-284, Springer, Berlin, Heidelberg, 2006. 10.1007\/11681878_14","DOI":"10.1007\/11681878_14"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] C. Dwork, K. Kenthapadi, F. McSherry, I. Mironov, and M. Naor, \u201cOur data, ourselves: Privacy via distributed noise generation,\u201d Advances in Cryptology - EUROCRYPT 2006, pp.486-503, Springer Berlin Heidelberg, 2006. 10.1007\/11761679_29","DOI":"10.1007\/11761679_29"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] C. Dwork, G.N. Rothblum, and S. Vadhan, \u201cBoosting and differential privacy,\u201d 2010 IEEE 51st Annual Symposium on Foundations of Computer Science, Las Vegas, NV, USA, pp.51-60, 2010. 10.1109\/focs.2010.12","DOI":"10.1109\/FOCS.2010.12"},{"key":"14","doi-asserted-by":"publisher","unstructured":"[14] A.R. Esposito, M. Gastpar, and I. Issa, \u201cGeneralization error bounds via R\u00e9nyi-, <i>f<\/i>-divergences and maximal leakage,\u201d IEEE Trans. Inf. Theory, vol.67, no.8, pp.4986-5004, 2021. 10.1109\/tit.2021.3085190","DOI":"10.1109\/TIT.2021.3085190"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] A. Evfimievski, J. Gehrke, and R. Srikant, \u201cLimiting privacy breaches in privacy preserving data mining,\u201d ACM PODS, pp.211-222, 2003. 10.1145\/773153.773174","DOI":"10.1145\/773153.773174"},{"key":"16","unstructured":"[16] S. Gopi, Y.T. Lee, and L. Wutschitz, \u201cNumerical composition of differential privacy,\u201d Advances in Neural Information Processing Systems, vol.34, pp.11631-11642, 2021."},{"key":"17","doi-asserted-by":"publisher","unstructured":"[17] P. Harremo\u00ebs and I. Vajda, \u201cOn pairs of <i>f<\/i>-divergences and their joint range,\u201d IEEE Trans. Inf. Theory, vol.57, no.6, pp.3230-3235, 2011. 10.1109\/tit.2011.2137353","DOI":"10.1109\/TIT.2011.2137353"},{"key":"18","doi-asserted-by":"publisher","unstructured":"[18] S.P. Kasiviswanathan, H.K. Lee, K. Nissim, S. Raskhodnikova, and A. Smith, \u201cWhat can we learn privately?,\u201d SIAM J. Comput., vol.40, no.3, pp.793-826, 2011. 10.1137\/090756090","DOI":"10.1137\/090756090"},{"key":"19","unstructured":"[19] A. Koskela, J. J\u00e4lk\u00f6, L. Prediger, and A. Honkela, \u201cTight differential privacy for discrete-valued mechanisms and for the subsampled gaussian mechanism using FFT,\u201d International Conference on Artificial Intelligence and Statistics, PMLR, vol.130, 2021."},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] I. Mironov, \u201cR\u00e9nyi differential privacy,\u201d 2017 IEEE 30th Computer Security Foundations Symposium (CSF), Santa Barbara, CA, USA, pp.263-275, 2017. 10.1109\/csf.2017.11","DOI":"10.1109\/CSF.2017.11"},{"key":"21","unstructured":"[21] A. R\u00e9nyi, \u201cOn measures of entropy and information,\u201d Berkeley Symp. on Math. Statist. and Prob., pp.547-561, 1961."},{"key":"22","doi-asserted-by":"publisher","unstructured":"[22] I. Sason and S. Verd\u00fa, \u201c<i>f<\/i>-divergence inequalities,\u201d IEEE Trans. Inf. Theory, vol.62, no.11, pp.5973-6006, 2016. 10.1109\/TIT.2016.2603151","DOI":"10.1109\/TIT.2016.2603151"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] B. Zamanlooy and S. Asoodeh, \u201cStrong data processing inequalities for locally differentially private mechanisms,\u201d 2023 IEEE International Symposium on Information Theory (ISIT), Taipei, pp.1794-1799, 2023. 10.1109\/isit54713.2023.10206578","DOI":"10.1109\/ISIT54713.2023.10206578"}],"container-title":["IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E108.A\/9\/E108.A_2024EAP1123\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T03:34:35Z","timestamp":1757129675000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E108.A\/9\/E108.A_2024EAP1123\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,1]]},"references-count":23,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1587\/transfun.2024eap1123","relation":{},"ISSN":["0916-8508","1745-1337"],"issn-type":[{"type":"print","value":"0916-8508"},{"type":"electronic","value":"1745-1337"}],"subject":[],"published":{"date-parts":[[2025,9,1]]},"article-number":"2024EAP1123"}}