{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:41:17Z","timestamp":1774917677311,"version":"3.50.1"},"reference-count":31,"publisher":"Elsevier BV","issue":"1","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,10,10]],"date-time":"2023-10-10T00:00:00Z","timestamp":1696896000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872205"],"award-info":[{"award-number":["61872205"]}],"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":["62172377"],"award-info":[{"award-number":["62172377"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2019MF018"],"award-info":[{"award-number":["ZR2019MF018"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["High-Confidence Computing"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1016\/j.hcc.2023.100167","type":"journal-article","created":{"date-parts":[[2023,10,12]],"date-time":"2023-10-12T12:24:05Z","timestamp":1697113445000},"page":"100167","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":17,"title":["Security defense strategy algorithm for Internet of Things based on deep reinforcement learning"],"prefix":"10.1016","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4243-5400","authenticated-orcid":false,"given":"Xuecai","family":"Feng","sequence":"first","affiliation":[]},{"given":"Jikai","family":"Han","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4117-2656","authenticated-orcid":false,"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Shuo","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Hui","family":"Xia","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.hcc.2023.100167_b1","doi-asserted-by":"crossref","first-page":"2300","DOI":"10.1109\/JIOT.2020.3025916","article-title":"Convergence of blockchain and edge computing for secure and scalable IIoT critical infrastructures in industry 4.0","volume":"8","author":"Wu","year":"2021","journal-title":"IEEE Internet Things J."},{"issue":"11","key":"10.1016\/j.hcc.2023.100167_b2","doi-asserted-by":"crossref","first-page":"8707","DOI":"10.1109\/JIOT.2020.3045653","article-title":"Recent advances in the internet-of-medical-things (IoMT) systems security","volume":"8","author":"Ghubaish","year":"2021","journal-title":"IEEE Internet Things J."},{"issue":"8","key":"10.1016\/j.hcc.2023.100167_b3","doi-asserted-by":"crossref","first-page":"4881","DOI":"10.1109\/TMC.2022.3164325","article-title":"Private data trading towards range counting queries in internet of things","volume":"22","author":"Cai","year":"2023","journal-title":"IEEE Trans. Mob. Comput."},{"key":"10.1016\/j.hcc.2023.100167_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.cose.2021.102494","article-title":"The internet of things security: A survey encompassing unexplored areas and new insights","volume":"112","author":"Omolara","year":"2022","journal-title":"Comput. Secur."},{"key":"10.1016\/j.hcc.2023.100167_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.iot.2019.100129","article-title":"A survey on internet of things security: Requirements, challenges, and solutions","volume":"14","author":"HaddadPajouh","year":"2021","journal-title":"Internet Things"},{"issue":"4","key":"10.1016\/j.hcc.2023.100167_b6","first-page":"577","article-title":"Collective data-sanitization for preventing sensitive information inference attacks in social networks","volume":"15","author":"Cai","year":"2018","journal-title":"IEEE Trans. Dependable Secure Comput."},{"issue":"11","key":"10.1016\/j.hcc.2023.100167_b7","doi-asserted-by":"crossref","first-page":"8693","DOI":"10.1109\/JIOT.2020.3040957","article-title":"Reinforcement learning for iot security: A comprehensive survey","volume":"8","author":"Uprety","year":"2021","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.hcc.2023.100167_b8","first-page":"1","article-title":"Deep reinforcement learning for cyber security","author":"Nguyen","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"1","key":"10.1016\/j.hcc.2023.100167_b9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s42400-019-0027-x","article-title":"Adversarial attack and defense in reinforcement learning-from AI security view","volume":"2","author":"Chen","year":"2019","journal-title":"Cybersecurity"},{"key":"10.1016\/j.hcc.2023.100167_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.comnet.2021.108004","article-title":"Deep reinforcement learning for blockchain in industrial IoT: A survey","volume":"191","author":"Wu","year":"2021","journal-title":"Comput. Netw."},{"issue":"2","key":"10.1016\/j.hcc.2023.100167_b11","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1109\/TNSE.2018.2830307","article-title":"A private and efficient mechanism for data uploading in smart cyber-physical systems","volume":"7","author":"Cai","year":"2020","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"key":"10.1016\/j.hcc.2023.100167_b12","series-title":"Markov game modeling of moving target defense for strategic detection of threats in cloud networks","author":"Chowdhary","year":"2019"},{"issue":"9","key":"10.1016\/j.hcc.2023.100167_b13","doi-asserted-by":"crossref","first-page":"2684","DOI":"10.1109\/TNNLS.2018.2885530","article-title":"A multistage game in smart grid security: A reinforcement learning solution","volume":"30","author":"Ni","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.hcc.2023.100167_b14","series-title":"Proceedings of the 16th International Conference on Network and Service Management","first-page":"1","article-title":"Finding effective security strategies through reinforcement learning and self-play","author":"Hammar","year":"2020"},{"key":"10.1016\/j.hcc.2023.100167_b15","series-title":"Learning security strategies through game play and optimal stopping","author":"Hammar","year":"2022"},{"key":"10.1016\/j.hcc.2023.100167_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.114896","article-title":"A deep reinforcement learning-based method applied for solving multi-agent defense and attack problems","volume":"176","author":"Huang","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.hcc.2023.100167_b17","series-title":"Multi-agent reinforcement learning in bayesian stackelberg markov games for adaptive moving target defense","author":"Sengupta","year":"2020"},{"key":"10.1016\/j.hcc.2023.100167_b18","doi-asserted-by":"crossref","first-page":"4101","DOI":"10.1109\/TIFS.2021.3103062","article-title":"Multi-agent reinforcement learning-based buffer-aided relay selection in IRS-assisted secure cooperative networks","volume":"16","author":"Huang","year":"2021","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"issue":"22","key":"10.1016\/j.hcc.2023.100167_b19","doi-asserted-by":"crossref","first-page":"22095","DOI":"10.1109\/JIOT.2021.3081626","article-title":"Multiagent federated reinforcement learning for secure incentive mechanism in intelligent cyber-physical systems","volume":"9","author":"Xu","year":"2021","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.hcc.2023.100167_b20","series-title":"2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS)","first-page":"144","article-title":"Trading private range counting over big IoT data","author":"Cai","year":"2019"},{"issue":"9","key":"10.1016\/j.hcc.2023.100167_b21","doi-asserted-by":"crossref","first-page":"3826","DOI":"10.1109\/TCYB.2020.2977374","article-title":"Deep reinforcement learning for multiagent systems: A review of challenges, solutions, and applications","volume":"50","author":"Nguyen","year":"2020","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.hcc.2023.100167_b22","doi-asserted-by":"crossref","first-page":"5023","DOI":"10.1007\/s10462-022-10299-x","article-title":"Deep multiagent reinforcement learning: challenges and directions","volume":"56","author":"Wong","year":"2023","journal-title":"Artif. Intell. Rev."},{"issue":"5","key":"10.1016\/j.hcc.2023.100167_b23","doi-asserted-by":"crossref","first-page":"968","DOI":"10.1109\/JSAC.2020.2980802","article-title":"Privacy-preserved data sharing towards multiple parties in industrial IoTs","volume":"38","author":"Zheng","year":"2020","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"10.1016\/j.hcc.2023.100167_b24","series-title":"Proceedings of the 37th Conference on Uncertainty in Artificial Intelligence, Vol. 161","first-page":"64","article-title":"Competitive policy optimization","author":"Prajapat","year":"2021"},{"issue":"7782","key":"10.1016\/j.hcc.2023.100167_b25","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in StarCraft II using multi-agent reinforcement learning","volume":"575","author":"Vinyals","year":"2019","journal-title":"Nature"},{"key":"10.1016\/j.hcc.2023.100167_b26","series-title":"Proceedings of the 37th International Conference on Machine Learning, Vol. 119","first-page":"507","article-title":"Agent57: Outperforming the atari human benchmark","author":"Badia","year":"2020"},{"key":"10.1016\/j.hcc.2023.100167_b27","series-title":"Proceedings of the 33nd International Conference on Machine Learning, Vol. 48","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"Wang","year":"2016"},{"key":"10.1016\/j.hcc.2023.100167_b28","series-title":"Proceedings of the 36th International Conference on Machine Learning, Vol. 97","first-page":"941","article-title":"Learning action representations for reinforcement learning","author":"Chandak","year":"2019"},{"key":"10.1016\/j.hcc.2023.100167_b29","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.hcc.2023.100167_b30","series-title":"Proceedings of the 32th AAAI Conference on Artificial Intelligence, Vol. 32","first-page":"1103","article-title":"Policy learning for continuous space security games using neural networks","author":"Kamra","year":"2018"},{"key":"10.1016\/j.hcc.2023.100167_b31","first-page":"4190","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","volume":"30","author":"Lanctot","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["High-Confidence Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S266729522300065X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S266729522300065X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T23:09:04Z","timestamp":1762643344000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S266729522300065X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["S266729522300065X"],"URL":"https:\/\/doi.org\/10.1016\/j.hcc.2023.100167","relation":{},"ISSN":["2667-2952"],"issn-type":[{"value":"2667-2952","type":"print"}],"subject":[],"published":{"date-parts":[[2024,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Security defense strategy algorithm for Internet of Things based on deep reinforcement learning","name":"articletitle","label":"Article Title"},{"value":"High-Confidence Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.hcc.2023.100167","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 The Author(s). Published by Elsevier B.V. on behalf of Shandong University.","name":"copyright","label":"Copyright"}],"article-number":"100167"}}