{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:42:59Z","timestamp":1784302979254,"version":"3.55.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["62002075"],"award-info":[{"award-number":["62002075"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102107"],"award-info":[{"award-number":["62102107"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072132"],"award-info":[{"award-number":["62072132"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62002074"],"award-info":[{"award-number":["62002074"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1936218"],"award-info":[{"award-number":["U1936218"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovation Research for the Postgraduates of Guangzhou University","award":["2020GDJCM23"],"award-info":[{"award-number":["2020GDJCM23"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Dependable and Secure Comput."],"published-print":{"date-parts":[[2023,1,1]]},"DOI":"10.1109\/tdsc.2022.3143566","type":"journal-article","created":{"date-parts":[[2022,1,18]],"date-time":"2022-01-18T22:08:39Z","timestamp":1642543719000},"page":"758-768","source":"Crossref","is-referenced-by-count":68,"title":["Attacking Deep Reinforcement Learning With Decoupled Adversarial Policy"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3762-674X","authenticated-orcid":false,"given":"Kanghua","family":"Mo","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence and Blockchain, Guangzhou University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4082-1140","authenticated-orcid":false,"given":"Weixuan","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Blockchain, Guangzhou University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0385-8793","authenticated-orcid":false,"given":"Jin","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Blockchain, Guangzhou University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3775-3033","authenticated-orcid":false,"given":"Xu","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, LA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","article-title":"Agent57: Outperforming the atari human benchmark","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Badia"},{"key":"ref3","article-title":"Mastering atari with discrete world models","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Hafner"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"issue":"1","key":"ref6","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref7","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Kalashnikov"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2019.2955905"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3046646"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2020.3034721"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/int.22315"},{"key":"ref13","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Goodfellow"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/int.22267"},{"key":"ref15","first-page":"2040","article-title":"Robust deep reinforcement learning with adversarial attacks","author":"Pattanaik","year":"2018"},{"key":"ref16","article-title":"Adversarial attacks on neural network policies","author":"Huang","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.2974509"},{"key":"ref18","article-title":"Delving into adversarial attacks on deep policies","author":"Kos","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/525"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6047"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref23","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref24","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref25","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/int.22778"},{"key":"ref27","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref28","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2014"},{"key":"ref29","article-title":"Adversarial examples in the physical world","author":"Kurakin","year":"2016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012253"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref33","article-title":"Transferability in machine learning: from phenomena to black-box attacks using adversarial samples","author":"Papernot","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140448"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301742"},{"key":"ref36","article-title":"Decision-based adversarial attacks: Reliable attacks against black-box machine learning models","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Brendel"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3345660"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2021.3088661"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.csi.2021.103612"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978392"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00009"},{"key":"ref42","first-page":"49","article-title":"Commandersong: A systematic approach for practical adversarial voice recognition","volume-title":"Proc. 27th USENIX Secur. Symp.","author":"Yuan"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1316"},{"key":"ref44","article-title":"Generating natural adversarial examples","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Zhao"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1002\/int.22260"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-62416-7_19"},{"key":"ref47","article-title":"Sequential attacks on agents for long-term adversarial goals","author":"Tretschk","year":"2018"},{"key":"ref48","first-page":"548","article-title":"Copycat: taking control of neural policies with constant attacks","volume-title":"Proc. 19th Int. Conf. Auton. Agents Multi-Agent Syst.","author":"Hussenot"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3390\/a13110268"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref51","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref53","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2016"},{"key":"ref54","article-title":"Emergent tool use from multi-agent autocurricula","author":"Baker","year":"2020"},{"key":"ref55","article-title":"Pettingzoo: Gym for multi-agent reinforcement learning","author":"Terry","year":"2020"}],"container-title":["IEEE Transactions on Dependable and Secure Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8858\/10016903\/09684689.pdf?arnumber=9684689","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T22:34:08Z","timestamp":1705185248000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9684689\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,1]]},"references-count":55,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tdsc.2022.3143566","relation":{},"ISSN":["1545-5971","1941-0018","2160-9209"],"issn-type":[{"value":"1545-5971","type":"print"},{"value":"1941-0018","type":"electronic"},{"value":"2160-9209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,1]]}}}