{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T19:50:20Z","timestamp":1761767420193,"version":"3.40.5"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T00:00:00Z","timestamp":1741046400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T00:00:00Z","timestamp":1741046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61502230,61501224"],"award-info":[{"award-number":["61502230,61501224"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20201357"],"award-info":[{"award-number":["BK20201357"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010014","name":"Six Talent Peaks Project in Jiangsu Province","doi-asserted-by":"publisher","award":["RJFW-020"],"award-info":[{"award-number":["RJFW-020"]}],"id":[{"id":"10.13039\/501100010014","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Peer-to-Peer Netw. Appl."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s12083-025-01939-4","type":"journal-article","created":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T12:27:15Z","timestamp":1741091235000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Collaborative path penetration in 5G-IoT networks: A multi-agent deep reinforcement learning approach"],"prefix":"10.1007","volume":"18","author":[{"given":"Hang","family":"Shen","sequence":"first","affiliation":[]},{"given":"Xiang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Tianjing","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Guangwei","family":"Bai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,4]]},"reference":[{"key":"1939_CR1","doi-asserted-by":"crossref","unstructured":"Lilhore UK, Dalal S, Simaiya S (2024) A cognitive security framework for detecting intrusions in IoT and 5G utilizing deep learning. Comput Sec 136:103560","DOI":"10.1016\/j.cose.2023.103560"},{"issue":"7","key":"1939_CR2","doi-asserted-by":"publisher","first-page":"7071","DOI":"10.1109\/TVT.2021.3083255","volume":"70","author":"H Shen","year":"2021","unstructured":"Shen H, Ye Q, Zhuang W, Shi W, Bai G, Yang G (2021) Drone-small-cell-assisted resource slicing for 5G uplink radio access networks. IEEE Trans Veh Technol 70(7):7071\u20137086","journal-title":"IEEE Trans Veh Technol"},{"issue":"1","key":"1939_CR3","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/s12083-023-01595-6","volume":"17","author":"F Li","year":"2024","unstructured":"Li F, Shen H, Mai J, Wang T, Dai Y, Miao X (2024) Pre-trained language model-enhanced conditional generative adversarial networks for intrusion detection. Peer-to-Peer Netw Appl 17(1):227\u2013245","journal-title":"Peer-to-Peer Netw Appl"},{"issue":"4","key":"1939_CR4","doi-asserted-by":"publisher","first-page":"3453","DOI":"10.1109\/COMST.2018.2855563","volume":"20","author":"I Stellios","year":"2018","unstructured":"Stellios I, Kotzanikolaou P, Psarakis M, Alcaraz C, Lopez J (2018) A survey of IoT-enabled cyberattacks: Assessing attack paths to critical infrastructures and services. IEEE Comm Surv Tutor 20(4):3453\u20133495","journal-title":"IEEE Comm Surv Tutor"},{"issue":"10","key":"1939_CR5","doi-asserted-by":"publisher","first-page":"2506","DOI":"10.1109\/TIFS.2018.2821095","volume":"13","author":"X Sun","year":"2018","unstructured":"Sun X, Dai J, Liu P, Singhal A, Yen J (2018) Using Bayesian networks for probabilistic identification of zero-day attack paths. IEEE Trans Inf Forensics Secur 13(10):2506\u20132521","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"1939_CR6","doi-asserted-by":"crossref","unstructured":"Jayasuryapal G, Pranay PM, Kaur H et\u00a0al (2021) A survey on network penetration testing. In international conference on intelligent engineering and management (ICIEM), pp 373\u2013378","DOI":"10.1109\/ICIEM51511.2021.9445321"},{"key":"1939_CR7","unstructured":"Hu H, Liu Y, Zhang H, Yang Y, Ye R (2018) Route prediction method for network intrusion using absorbing markov chain. J Comput Res Dev 55(4):831\u2013845"},{"key":"1939_CR8","first-page":"129","volume":"8","author":"I Kotenko","year":"2012","unstructured":"Kotenko I, Chechulin A (2012) Attack modeling and security evaluation in siem systems. Int Trans Syst Sci Appl 8:129\u2013147","journal-title":"Int Trans Syst Sci Appl"},{"key":"1939_CR9","doi-asserted-by":"crossref","unstructured":"Fang X, Zhai L, Jia Z, Bai W (2014) A game model for predicting the attack path of apt. In IEEE 12th international conference on dependable, autonomic and secure computing, pp 491\u2013495","DOI":"10.1109\/DASC.2014.94"},{"issue":"5","key":"1939_CR10","doi-asserted-by":"publisher","first-page":"4009","DOI":"10.1109\/TMC.2023.3283852","volume":"23","author":"H Shen","year":"2023","unstructured":"Shen H, Tian Y, Wang T, Bai G (2023) Slicing-based task offloading in space-air-ground integrated vehicular networks. IEEE Trans Mob Comput 23(5):4009\u20134024","journal-title":"IEEE Trans Mob Comput"},{"key":"1939_CR11","doi-asserted-by":"crossref","unstructured":"Uprety A, Rawat DB (2020) Reinforcement learning for IoT security: A comprehensive survey. IEEE Internet Things J 8(11):8693\u20138706","DOI":"10.1109\/JIOT.2020.3040957"},{"issue":"4","key":"1939_CR12","doi-asserted-by":"publisher","first-page":"6932","DOI":"10.1109\/LRA.2020.3026638","volume":"5","author":"B Wang","year":"2020","unstructured":"Wang B, Liu Z, Li Q, Prorok A (2020) Mobile robot path planning in dynamic environments through globally guided reinforcement learning. IEEE Robot Autom Lett 5(4):6932\u20136939","journal-title":"IEEE Robot Autom Lett"},{"key":"1939_CR13","doi-asserted-by":"crossref","unstructured":"Cody T, Rahman A, Redino C, Huang L, Clark R, Kakkar A, Kushwaha D, Park P, Beling P, Bowen E (2022) Discovering exfiltration paths using reinforcement learning with attack graphs. In IEEE conference on dependable and secure computing (DSC), pp 1\u20138","DOI":"10.1109\/DSC54232.2022.9888919"},{"issue":"1","key":"1939_CR14","first-page":"6008447","volume":"2022","author":"L Zhang","year":"2022","unstructured":"Zhang L, Li H, Shiming Xia Y, Pan WB, Feng Q, Li Wei, Zheng Qibin, Guo Shize, Pan Zhisong (2022) Discover the hidden attack path in multiple domain cyberspace based on reinforcement learning. Sci Program 2022(1):6008447","journal-title":"Sci Program"},{"key":"1939_CR15","doi-asserted-by":"crossref","unstructured":"Hu Z, Beuran R, Tan Y (2020) Automated penetration testing using deep reinforcement learning. In IEEE European symposium on security and privacy workshops (EuroS &PW), p 2\u201310","DOI":"10.1109\/EuroSPW51379.2020.00010"},{"key":"1939_CR16","doi-asserted-by":"crossref","unstructured":"Somesula MK, Rout RR, Somayajulu DVLN (2022) Cooperative cache update using multi-agent recurrent deep reinforcement learning for mobile edge networks. Comput Netw 209:108876","DOI":"10.1016\/j.comnet.2022.108876"},{"issue":"7","key":"1939_CR17","doi-asserted-by":"publisher","first-page":"8762","DOI":"10.1109\/TNNLS.2023.3236361","volume":"35","author":"J Hao","year":"2024","unstructured":"Hao J, Yang T, Tang H, Bai C, Liu J, Meng Z, Liu P, Wang Z (2024) Exploration in deep reinforcement learning: From single-agent to multiagent domain. IEEE Trans Neural Netw LearnSyst 35(7):8762\u20138782","journal-title":"IEEE Trans Neural Netw LearnSyst"},{"issue":"12","key":"1939_CR18","doi-asserted-by":"publisher","first-page":"13914","DOI":"10.1109\/TMC.2024.3439016","volume":"23","author":"X Li","year":"2024","unstructured":"Li X, Huangfu W, Xinyi X, Huo J, Long K (2024) Secure offloading with adversarial multi-agent reinforcement learning against intelligent eavesdroppers in uav-enabled mobile edge computing. IEEE Trans Mob Comput 23(12):13914\u201313928","journal-title":"IEEE Trans Mob Comput"},{"key":"1939_CR19","doi-asserted-by":"crossref","unstructured":"Ju Y, Chen Y, Cao Z, Liu L, Pei Q, Xiao M, Ota K, Dong M, Leung VCM (2023) Joint secure offloading and resource allocation for vehicular edge computing network: A multi-agent deep reinforcement learning approach. IEEE Trans Intell Transp Syst 24(5):5555\u20135569, 2023","DOI":"10.1109\/TITS.2023.3242997"},{"issue":"1","key":"1939_CR20","first-page":"5381495","volume":"2020","author":"X Liu","year":"2020","unstructured":"Liu X, Zhang H, Zhang Y, Shao L (2020) Optimal network defense strategy selection method based on evolutionary network game. Secur Commun Netw 2020(1):5381495","journal-title":"Secur Commun Netw"},{"key":"1939_CR21","doi-asserted-by":"crossref","unstructured":"Khan AA, Wagan AA, Laghari AA, Gilal AR, Aziz IA, Talpur BA (2022) Biomt: A state-of-the-art consortium serverless network architecture for healthcare system using blockchain smart contracts. IEEE Access 10:78887\u201378898","DOI":"10.1109\/ACCESS.2022.3194195"},{"key":"1939_CR22","first-page":"101","volume":"11","author":"D Atzmon","year":"2020","unstructured":"Atzmon D, Zax Y, Kivity E, Avitan L, Morag J, Felner A (2020) Generalizing multi-agent path finding for heterogeneous agents. Proc Int Symp Comb Search 11:101\u2013105","journal-title":"Proc Int Symp Comb Search"},{"key":"1939_CR23","doi-asserted-by":"crossref","unstructured":"Sharma PK, Fernandez R, Zaroukian E, Dorothy M, Basak A, Asher DE (2021) Survey of recent multi-agent reinforcement learning algorithms utilizing centralized training. In artificial intelligence and machine learning for multi-domain operations applications III, vol 11746. pp 665\u2013676","DOI":"10.1117\/12.2585808"},{"key":"1939_CR24","doi-asserted-by":"crossref","unstructured":"Rawat DB, Njilla L, Kwiat K, Kamhoua C (2018) iShare: Blockchain-based privacy-aware multi-agent information sharing games for cybersecurity. In international conference on computing, networking and communications (ICNC), pp 425\u2013431","DOI":"10.1109\/ICCNC.2018.8390264"},{"issue":"2","key":"1939_CR25","doi-asserted-by":"publisher","first-page":"729","DOI":"10.1109\/TWC.2019.2935201","volume":"19","author":"J Cui","year":"2019","unstructured":"Cui J, Liu Y, Nallanathan A (2019) Multi-agent reinforcement learning-based resource allocation for UAV networks. IEEE Trans Wireless Commun 19(2):729\u2013743","journal-title":"IEEE Trans Wireless Commun"},{"issue":"2","key":"1939_CR26","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1006\/pmpp.1999.0218","volume":"55","author":"RM Bostock","year":"1999","unstructured":"Bostock RM (1999) Signal conflicts and synergies in induced resistance to multiple attackers. Physiol Mol Plant Pathol 55(2):99\u2013109","journal-title":"Physiol Mol Plant Pathol"},{"key":"1939_CR27","doi-asserted-by":"crossref","unstructured":"Hausken K, Bier VM (2011) Defending against multiple different attackers. Eur J Oper Res 211(2):370\u2013384","DOI":"10.1016\/j.ejor.2010.12.013"},{"issue":"1\u20132","key":"1939_CR28","first-page":"59","volume":"6","author":"B Bertenyi","year":"2018","unstructured":"Bertenyi B, Burbidge R, Masini G, Sirotkin S, Gao Y (2018) Ng radio access network (ng-ran). J ICT Stand 6(1\u20132):59\u201376","journal-title":"J ICT Stand"},{"key":"1939_CR29","doi-asserted-by":"crossref","unstructured":"Khichane A, Fajjari I, Aitsaadi N, Gueroui M (2023) 5GC-Observer: a non-intrusive observability framework for cloud native 5G system. In IEEE\/IFIP network operations and management symposium (NOMS), pp 1\u201310","DOI":"10.1109\/NOMS56928.2023.10154433"},{"key":"1939_CR30","doi-asserted-by":"crossref","unstructured":"Lin CS (2022) A lightweight design of 5g private network with edge computing. In Int Conf Mechatronics Technol (ICMT), pp 1\u20132","DOI":"10.1109\/ICMT56556.2022.9997658"},{"key":"1939_CR31","doi-asserted-by":"crossref","unstructured":"Ikeda T, Shibuya T (2022) Centralized training with decentralized execution reinforcement learning for cooperative multi-agent systems with communication delay. In annual conference of the society of instrument and control engineers (SICE), pp 135\u2013140","DOI":"10.23919\/SICE56594.2022.9905866"},{"key":"1939_CR32","unstructured":"Branzei R, Dimitrov D, Tijs S (2008) Models in cooperative game theory, vol 556. Springer Science & Business Media"},{"key":"1939_CR33","doi-asserted-by":"crossref","unstructured":"Shapley LS (1953) A value for n-person games. Contribution to the Theory of Games, 2","DOI":"10.1515\/9781400881970-018"},{"key":"1939_CR34","doi-asserted-by":"crossref","unstructured":"Nash JF Jr (1950) Equilibrium points in n-person games. Proc Natl Academy Sci 36(1):48\u201349","DOI":"10.1073\/pnas.36.1.48"},{"issue":"3","key":"1939_CR35","doi-asserted-by":"publisher","first-page":"2393","DOI":"10.1002\/int.22778","volume":"37","author":"K Wan","year":"2022","unstructured":"Wan K, Dingwei W, Li B, Gao X, Zijian H, Chen D (2022) ME-MADDPG: An efficient learning-based motion planning method for multiple agents in complex environments. Int J Intell Syst 37(3):2393\u20132427","journal-title":"Int J Intell Syst"},{"key":"1939_CR36","first-page":"12208","volume":"34","author":"Factored multi-agent centralised policy gradients","year":"2021","unstructured":"Factored multi-agent centralised policy gradients (2021) Bei Peng, Tabish Rashid, Christian Schroeder de Witt, Pierre-Alexandre Kamienny, Philip Torr, Wendelin B\u00f6hmer, and Shimon Whiteson. Facmac. Adv Neural Inf Process Syst 34:12208\u201312221","journal-title":"Adv Neural Inf Process Syst"},{"issue":"3","key":"1939_CR37","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1109\/TITS.2019.2901791","volume":"21","author":"T Chu","year":"2019","unstructured":"Chu T, Wang J, Codec\u00e0 L, Li Z (2019) Multi-agent deep reinforcement learning for large-scale traffic signal control. IEEE Trans Intell Transp Syst 21(3):1086\u20131095","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"1939_CR38","doi-asserted-by":"crossref","unstructured":"Shi H, Tian Y, Li H, Huang J, Shi L, Zhou Y (2024) Task offloading and trajectory scheduling for UAV-enabled MEC networks: An madrl algorithm with prioritized experience replay. Ad Hoc Netw 154","DOI":"10.1016\/j.adhoc.2023.103371"}],"container-title":["Peer-to-Peer Networking and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12083-025-01939-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12083-025-01939-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12083-025-01939-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T02:31:33Z","timestamp":1746844293000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12083-025-01939-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,4]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["1939"],"URL":"https:\/\/doi.org\/10.1007\/s12083-025-01939-4","relation":{},"ISSN":["1936-6442","1936-6450"],"issn-type":[{"type":"print","value":"1936-6442"},{"type":"electronic","value":"1936-6450"}],"subject":[],"published":{"date-parts":[[2025,3,4]]},"assertion":[{"value":"13 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval and Consent to Participate"}},{"value":"All authors agree to publish the paper and related research results of the paper.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}],"article-number":"113"}}