{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T00:02:15Z","timestamp":1755993735481,"version":"3.44.0"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972025","61802389","61672092","U1811264","61966009"],"award-info":[{"award-number":["61972025","61802389","61672092","U1811264","61966009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2020YFB1005604","2020YFB2103802"],"award-info":[{"award-number":["2020YFB1005604","2020YFB2103802"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tai.2022.3190811","type":"journal-article","created":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T15:43:10Z","timestamp":1657813390000},"page":"1089-1100","source":"Crossref","is-referenced-by-count":0,"title":["A Mutual Information-Based Assessment of Reverse Engineering on Rewards of Reinforcement Learning"],"prefix":"10.1109","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3851-2135","authenticated-orcid":false,"given":"Tong","family":"Chen","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1147-4327","authenticated-orcid":false,"given":"Jiqiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5166-4873","authenticated-orcid":false,"given":"Thar","family":"Baker","sequence":"additional","affiliation":[{"name":"Department of Computer Science, College of Computing and Informatics, University of Sharjah, Sharjah, United Arab Emirates"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0891-1904","authenticated-orcid":false,"given":"Yalun","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China"}]},{"given":"Yingxiao","family":"Xiang","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6693-0935","authenticated-orcid":false,"given":"Yike","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4706-4266","authenticated-orcid":false,"given":"Wenjia","family":"Niu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0348-2108","authenticated-orcid":false,"given":"Endong","family":"Tong","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3090-1059","authenticated-orcid":false,"given":"Albert Y.","family":"Zomaya","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Sydney, Sydney, Australia"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1057\/jt.2009.16"},{"key":"ref35","first-page":"1","article-title":"A game-theoretic approach to apprenticeship learning","volume":"20","author":"syed","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref12","first-page":"216","article-title":"New method based on interquartile range to feature selection for classification in big data","author":"kocat\u00fcrk","year":"0","journal-title":"Prpc 5th Int Researchers Statisticians Young Statisticians Congr"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143936"},{"key":"ref15","first-page":"1","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"ng","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICST46399.2020.00049"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.22271\/allresearch.2021.v7.i4c.8484"},{"journal-title":"Finding Groups in Data An Introduction to Cluster Analysis","year":"2009","author":"kaufman","key":"ref30"},{"key":"ref11","first-page":"77","article-title":"Explicit scale estimators with high breakdown point","volume":"1","author":"rousseeuw","year":"0","journal-title":"L1 Statistical Analyses and Related Methods"},{"key":"ref33","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"ziebart","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2014.7090537"},{"key":"ref32","first-page":"1","article-title":"Nonlinear inverse reinforcement learning with gaussian processes","volume":"24","author":"levine","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"article-title":"A survey of behavior learning applications in robotics–state of the art and perspectives","year":"2019","author":"fabisch","key":"ref1"},{"key":"ref17","first-page":"1","article-title":"Inverse optimal control with linearly-solvable MDPs","author":"dvijotham","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9121-3"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10896"},{"key":"ref23","first-page":"32","article-title":"The price of differential privacy for online learning","author":"agarwal","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","first-page":"5579","article-title":"An optimal private stochastic-MAB algorithm based on optimal private stopping rule","author":"sajed","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10212"},{"key":"ref20","first-page":"1","article-title":"Feature construction for inverse reinforcement learning","volume":"23","author":"levine","year":"2010","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref22","first-page":"5143","article-title":"Competitive multi-agent inverse reinforcement learning with sub-optimal demonstrations","author":"wang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","first-page":"1","article-title":"Inverse reinforcement learning from failure","author":"shiarlis","year":"0","journal-title":"Proc Int Found Auton Agents Multiagent Syst"},{"key":"ref28","first-page":"2130","article-title":"Differentially private policy evaluation","author":"balle","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","first-page":"1","article-title":"Differentially private contextual linear bandits","volume":"31","author":"shariff","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref29","first-page":"1","article-title":"Private Q-learning with functional noise in continuous spaces","author":"wang","year":"2019","journal-title":"CoRR"},{"article-title":"Horizon: Facebook's open source applied reinforcement learning platform","year":"2018","author":"gauci","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.2807"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2018.00038"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s42081-020-00091-y"},{"key":"ref3","first-page":"601","article-title":"Stealing machine learning models via prediction APIs","author":"tram\u00e8r","year":"0","journal-title":"Proc 25th USENIX Secur Symp"},{"journal-title":"CRC Standard Probability and Statistics Tables and Formulae","year":"2000","author":"kokoska","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8916952"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10261321\/09829911.pdf?arnumber=9829911","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:08:40Z","timestamp":1755911320000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9829911\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":35,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tai.2022.3190811","relation":{},"ISSN":["2691-4581"],"issn-type":[{"type":"electronic","value":"2691-4581"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}