{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:22:20Z","timestamp":1740169340951,"version":"3.37.3"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3402351","type":"journal-article","created":{"date-parts":[[2024,5,17]],"date-time":"2024-05-17T17:48:59Z","timestamp":1715968139000},"page":"70305-70317","source":"Crossref","is-referenced-by-count":0,"title":["Adversarial Reinforcement Learning Against Statistic Inference on Agent Identity"],"prefix":"10.1109","volume":"12","author":[{"given":"Yue","family":"Tian","sequence":"first","affiliation":[{"name":"School of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2276-2079","authenticated-orcid":false,"given":"Zuxing","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4548-3697","authenticated-orcid":false,"given":"Chao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/9781119785194"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2012.2194794"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CC.2014.6969789"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCOMSTD.001.1900053"},{"volume-title":"Stochastic Optimal Control: The Discrete- Time Case","year":"1978","author":"Bertsekas","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref8","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. ICLR","author":"Lillicrap"},{"key":"ref9","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. ICML","author":"Fujimoto"},{"key":"ref10","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/0471221082"},{"volume-title":"Deep Learning","year":"2016","author":"Goodfellow","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2720195"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2012.2211046"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2017.2744601"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2018.2809005"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3005634"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.3036247"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2844403"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3158663"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1536414.1536440"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2090236.2090262"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2553647"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3049222"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/11787006_1"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2944748"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3167015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2021.3081170"},{"key":"ref29","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. AISTATS","author":"McMahan"},{"key":"ref30","article-title":"Federated domain generalization: A survey","author":"Li","year":"2023","journal-title":"arXiv:2306.01334"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3230586"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2023.3292382"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2942593"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2023.3248320"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3174469"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.fa.2021-0825.202307"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2022.3218044"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/Allerton.2013.6736549"},{"key":"ref39","first-page":"368","article-title":"How you act tells a loT: Privacy-leakage attack on deep reinforcement learning","volume-title":"Proc. AAMAS","author":"Pan"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303900"},{"key":"ref41","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ng"},{"key":"ref42","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. 23rd AAAI Conf. Artif. Intell.","volume":"8","author":"Ziebart"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3302509.3311049"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483184"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2283096"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2017.2751458"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8431397"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303817"},{"key":"ref49","first-page":"11327","article-title":"Privacy-preserving Q-learning with functional noise in continuous spaces","volume-title":"Proc. NeurIPS","author":"Wang"},{"volume-title":"General Data Protection Regulation (GDPR)","year":"2022","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3390\/e24070856"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2068870"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3089823"},{"key":"ref56","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10534061.pdf?arnumber=10534061","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,24]],"date-time":"2024-05-24T04:56:39Z","timestamp":1716526599000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10534061\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3402351","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}