{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:35:21Z","timestamp":1778348121471,"version":"3.51.4"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030415785","type":"print"},{"value":"9783030415792","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-41579-2_39","type":"book-chapter","created":{"date-parts":[[2020,2,17]],"date-time":"2020-02-17T16:09:09Z","timestamp":1581955749000},"page":"668-683","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Differentially Private Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Pingchuan","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Le","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruming","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoxiang","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,2,18]]},"reference":[{"key":"39_CR1","doi-asserted-by":"crossref","unstructured":"Abadi, M., et al.: Deep learning with differential privacy. In: Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, pp. 308\u2013318. ACM (2016)","DOI":"10.1145\/2976749.2978318"},{"key":"39_CR2","unstructured":"Balle, B., Gomrokchi, M., Precup, D.: Differentially private policy evaluation. In: International Conference on Machine Learning, pp. 2130\u20132138 (2016)"},{"key":"39_CR3","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/978-94-015-3711-7","volume-title":"Bandit Problems: Sequential Allocation of Experiments (Monographs on Statistics and Applied Probability)","author":"DA Berry","year":"1985","unstructured":"Berry, D.A., Fristedt, B.: Bandit Problems: Sequential Allocation of Experiments (Monographs on Statistics and Applied Probability), vol. 5, pp. 71\u201387. Chapman and Hall, London (1985)"},{"key":"39_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-540-79228-4_1","volume-title":"Theory and Applications of Models of Computation","author":"C Dwork","year":"2008","unstructured":"Dwork, C.: Differential privacy: a survey of results. In: Agrawal, M., Du, D., Duan, Z., Li, A. (eds.) TAMC 2008. LNCS, vol. 4978, pp. 1\u201319. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-79228-4_1"},{"key":"39_CR5","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1007\/978-1-4419-5906-5","volume-title":"Encyclopedia of Cryptography and Security","author":"C Dwork","year":"2011","unstructured":"Dwork, C.: Differential privacy. In: van Tilborg, H.C.A., Jajodia, S. (eds.) Encyclopedia of Cryptography and Security, pp. 338\u2013340. Springer, Boston (2011). https:\/\/doi.org\/10.1007\/978-1-4419-5906-5"},{"issue":"1","key":"39_CR6","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1145\/1866739.1866758","volume":"54","author":"C Dwork","year":"2011","unstructured":"Dwork, C.: A firm foundation for private data analysis. Commun. ACM 54(1), 86\u201395 (2011)","journal-title":"Commun. ACM"},{"key":"39_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1007\/11681878_14","volume-title":"Theory of Cryptography","author":"C Dwork","year":"2006","unstructured":"Dwork, C., McSherry, F., Nissim, K., Smith, A.: Calibrating noise to sensitivity in private data analysis. In: Halevi, S., Rabin, T. (eds.) TCC 2006. LNCS, vol. 3876, pp. 265\u2013284. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11681878_14"},{"issue":"3\u20134","key":"39_CR8","first-page":"211","volume":"9","author":"C Dwork","year":"2014","unstructured":"Dwork, C., Roth, A., et al.: The algorithmic foundations of differential privacy. Found. Trends\u00ae Theoret. Comput. Sci. 9(3\u20134), 211\u2013407 (2014)","journal-title":"Found. Trends\u00ae Theoret. Comput. Sci."},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Erlingsson, \u00da., Pihur, V., Korolova, A.: RAPPOR: randomized aggregatable privacy-preserving ordinal response. In: Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications Security, pp. 1054\u20131067. ACM (2014)","DOI":"10.1145\/2660267.2660348"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Fredrikson, M., Jha, S., Ristenpart, T.: Model inversion attacks that exploit confidence information and basic countermeasures. In: Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, pp. 1322\u20131333. ACM (2015)","DOI":"10.1145\/2810103.2813677"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Friedman, A., Schuster, A.: Data mining with differential privacy. In: Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2010, pp. 493\u2013502. ACM, New York (2010)","DOI":"10.1145\/1835804.1835868"},{"key":"39_CR12","doi-asserted-by":"publisher","DOI":"10.1002\/9780470980033","volume-title":"Multi-Armed Bandit Allocation Indices","author":"J Gittins","year":"2011","unstructured":"Gittins, J., Glazebrook, K., Weber, R.: Multi-Armed Bandit Allocation Indices. Wiley, Hoboken (2011)"},{"key":"39_CR13","unstructured":"Jaakkola, T., Singh, S.P., Jordan, M.I.: Reinforcement learning algorithm for partially observable Markov decision problems. In: Advances in Neural Information Processing Systems, pp. 345\u2013352 (1995)"},{"key":"39_CR14","unstructured":"Ji, Z., Lipton, Z.C., Elkan, C.: Differential privacy and machine learning: a survey and review. arXiv preprint arXiv:1412.7584 (2014)"},{"issue":"3","key":"39_CR15","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1137\/090756090","volume":"40","author":"SP Kasiviswanathan","year":"2011","unstructured":"Kasiviswanathan, S.P., Lee, H.K., Nissim, K., Raskhodnikova, S., Smith, A.: What can we learn privately? SIAM J. Comput. 40(3), 793\u2013826 (2011)","journal-title":"SIAM J. Comput."},{"key":"39_CR16","unstructured":"Kuleshov, V., Precup, D.: Algorithms for multi-armed bandit problems. arXiv preprint arXiv:1402.6028 (2014)"},{"issue":"7553","key":"39_CR17","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015)","journal-title":"Nature"},{"key":"39_CR18","doi-asserted-by":"publisher","first-page":"12103","DOI":"10.1109\/ACCESS.2018.2805680","volume":"6","author":"Q Liu","year":"2018","unstructured":"Liu, Q., Li, P., Zhao, W., Cai, W., Yu, S., Leung, V.C.M.: A survey on security threats and defensive techniques of machine learning: a data driven view. IEEE Access 6, 12103\u201312117 (2018). https:\/\/doi.org\/10.1109\/ACCESS.2018.2805680","journal-title":"IEEE Access"},{"key":"39_CR19","unstructured":"Mishra, N., Thakurta, A.: (Nearly) optimal differentially private stochastic multi-arm bandits. In: Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, pp. 592\u2013601. AUAI Press (2015)"},{"key":"39_CR20","doi-asserted-by":"crossref","unstructured":"Nissim, K., Raskhodnikova, S., Smith, A.: Smooth sensitivity and sampling in private data analysis. In: Proceedings of the Thirty-ninth Annual ACM Symposium on Theory of Computing, pp. 75\u201384. ACM (2007)","DOI":"10.1145\/1250790.1250803"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Sakuma, J., Kobayashi, S., Wright, R.N.: Privacy-preserving reinforcement learning. In: Proceedings of the 25th International Conference on Machine learning, pp. 864\u2013871. ACM (2008)","DOI":"10.1145\/1390156.1390265"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Salem, A., Zhang, Y., Humbert, M., Berrang, P., Fritz, M., Backes, M.: ML-Leaks: model and data independent membership inference attacks and defenses on machine learning models. arXiv preprint arXiv:1806.01246 (2018)","DOI":"10.14722\/ndss.2019.23119"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Shokri, R., Stronati, M., Song, C., Shmatikov, V.: Membership inference attacks against machine learning models. In: 2017 IEEE Symposium on Security and Privacy (SP), pp. 3\u201318. IEEE (2017)","DOI":"10.1109\/SP.2017.41"},{"issue":"7\u20138","key":"39_CR24","doi-asserted-by":"publisher","first-page":"2031","DOI":"10.1007\/s00521-013-1362-6","volume":"23","author":"S Sun","year":"2013","unstructured":"Sun, S.: A survey of multi-view machine learning. Neural Comput. Appl. 23(7\u20138), 2031\u20132038 (2013)","journal-title":"Neural Comput. Appl."},{"key":"39_CR25","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"39_CR26","unstructured":"Tang, X., Zhu, L., Shen, M., Du, X.: When homomorphic cryptosystem meets differential privacy: training machine learning classifier with privacy protection. arXiv preprint arXiv:1812.02292 (2018)"},{"key":"39_CR27","doi-asserted-by":"crossref","unstructured":"Tossou, A.C., Dimitrakakis, C.: Algorithms for differentially private multi-armed bandits. In: Thirtieth AAAI Conference on Artificial Intelligence (2016)","DOI":"10.1609\/aaai.v30i1.10212"},{"key":"39_CR28","doi-asserted-by":"crossref","unstructured":"Wu, X., Fredrikson, M., Jha, S., Naughton, J.F.: A methodology for formalizing model-inversion attacks. In: 2016 IEEE 29th Computer Security Foundations Symposium (CSF), pp. 355\u2013370. IEEE (2016)","DOI":"10.1109\/CSF.2016.32"}],"container-title":["Lecture Notes in Computer Science","Information and Communications Security"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-41579-2_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,15]],"date-time":"2022-10-15T20:03:56Z","timestamp":1665864236000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-41579-2_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030415785","9783030415792"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-41579-2_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"18 February 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICICS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Information and Communications Security","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 December 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 December 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icics2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"199","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"47","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"8","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}