{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T06:06:40Z","timestamp":1770271600076,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":37,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819755806","type":"print"},{"value":"9789819755813","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-97-5581-3_41","type":"book-chapter","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T19:02:53Z","timestamp":1722538973000},"page":"504-516","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Optimal Defense Strategy for Multi-agents Using Value Decomposition Networks"],"prefix":"10.1007","author":[{"given":"Weixia","family":"Cai","sequence":"first","affiliation":[]},{"given":"Hong","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Huashan","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Feng","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,1]]},"reference":[{"key":"41_CR1","unstructured":"Chapple, M., Seidl, D.: CompTIA Security+ Study Guide: Exam SY0-601, 8th edn. Sybe, Indianapolis (2021)"},{"key":"41_CR2","doi-asserted-by":"crossref","unstructured":"Ioannidis, S., Keromytis, A.D., Bellovin, S.M., et al: Implementing a distributed firewall. In: Samarati, P.(eds.) CCS, pp. 190\u2013199. New York (2000)","DOI":"10.1145\/352600.353052"},{"key":"41_CR3","doi-asserted-by":"crossref","unstructured":"Chen, H., Cho, J.H., Xu, S.: Quantifying the security effectiveness of firewalls and DMZS. In: Proceedings of the 5th Annual Symposium and Bootcamp on Hot Topics in the Science of Security, pp. 1\u201311 (2018)","DOI":"10.1145\/3190619.3190639"},{"key":"41_CR4","doi-asserted-by":"crossref","unstructured":"Liao, H.J., Lin, C.H.R., Lin, Y.C., et al.: Intrusion detection system: a comprehensive review. J. Netw. Comput. Appl. 36(1), 16\u201324(2013)","DOI":"10.1016\/j.jnca.2012.09.004"},{"key":"41_CR5","doi-asserted-by":"crossref","unstructured":"Abu-Dabaseh, F., Alshammari, E.: Automated penetration testing: an overview. In: The 4th International Conference on Natural Language Computing, pp.121\u2013129, Copenhagen (2018)","DOI":"10.5121\/csit.2018.80610"},{"issue":"7587","key":"41_CR6","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.J., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"41_CR7","doi-asserted-by":"crossref","unstructured":"Silver, D., Schrittwieser, J., Simonyan, K., et al: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","DOI":"10.1038\/nature24270"},{"issue":"7782","key":"41_CR8","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., Babuschkin, I., Czarnecki, W.M., et al.: Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature, vul. 575(7782), 350\u2013354 (2019)","journal-title":"Nature, vul."},{"key":"41_CR9","doi-asserted-by":"crossref","unstructured":"Johannink, T., Bahl, S., Nair, A., et al: Residual reinforcement learning for robot control. ICRA, pp. 6023\u20136029. IEEE, Montreal (2019)","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"41_CR10","doi-asserted-by":"crossref","unstructured":"Li, Z., Cheng, X., Peng, X.B., et al: Reinforcement learning for robust parameterized locomotion control of bipedal robots. In: ICRA, pp. 2811\u20132817. IEEE, Xi\u2019an (2021)","DOI":"10.1109\/ICRA48506.2021.9560769"},{"key":"41_CR11","unstructured":"Weixia, C, Huashan, C., Feng, L: Keeping your enemies closer: shedding light on the attacker\u2019s optimal strategy. In: Yung, M., Chen, C., Meng, W. (eds.) Science of Cyber Security. LNCS, vol. 14299. Springer, Cham (2023)"},{"key":"41_CR12","unstructured":"Yu, J., Guo, W., Qin, Q., et al.: Explanation for deep reinforcement learning based security applications. In: USENIX Security, pp. 7375\u20137392. USENIX Association, Anaheim (2023)"},{"key":"41_CR13","unstructured":"Qianyu, L., Min, Z., Yi, S., et al: A hierarchical deep reinforcement learning model with expert prior knowledge for intelligent penetration testing. Comput. Secur. 0167\u20134048 (2023)"},{"key":"41_CR14","doi-asserted-by":"crossref","unstructured":"Foo, B., Glause, M.W., Howard, G.M., et al: Intrusion response systems: a survey. In: Information Assurance: Dependability and Security in Networked Systems, pp. 377\u2013416 (2008)","DOI":"10.1016\/B978-012373566-9.50015-X"},{"key":"41_CR15","doi-asserted-by":"crossref","unstructured":"Lewandowski, S.M., Van Hook, D.J., O\u2019Leary, G.C., et al: SARA: Survivable autonomic response architecture. In: DISCEX, pp. 77\u201388. IEEE, Anaheim (2001)","DOI":"10.21236\/ADA408307"},{"key":"41_CR16","doi-asserted-by":"crossref","unstructured":"Miehling, E., Rasouli, M., Teneketzis, D.: A POMDP approach to the dynamic defense of large-scale cyber networks. In: TIFS, pp. 2490\u20132505 IEEE (2018)","DOI":"10.1109\/TIFS.2018.2819967"},{"key":"41_CR17","doi-asserted-by":"crossref","unstructured":"Miehling, E., Rasouli, M., Teneketzis, D.: Optimal defense policies for partially observable spreading processes on Bayesian attack graphs. In: ACM Workshop Moving Target Defense, pp. 67\u201376 (2015)","DOI":"10.1145\/2808475.2808482"},{"issue":"1","key":"41_CR18","first-page":"1","volume":"24","author":"H Zhisheng","year":"2020","unstructured":"Zhisheng, H., Minghui, Z., Peng, L.: Adaptive cyber defense against multi-stage attacks using learning-based POMDP. ACM Trans. Privacy Secur. 24(1), 1\u201325 (2020)","journal-title":"ACM Trans. Privacy Secur."},{"key":"41_CR19","doi-asserted-by":"crossref","unstructured":"Holm, H.: Lore a red team emulation tool. In: TDSC, pp. 1596\u20131608. IEEE (2022)","DOI":"10.1109\/TDSC.2022.3160792"},{"key":"41_CR20","unstructured":"Berner, C., Brockman, G., Chan, B., et al.: Dota 2 with large scale deep reinforcement learning. arXiv preprint arXiv:1912.06680 (2019)"},{"key":"41_CR21","doi-asserted-by":"crossref","unstructured":"Liu, T., He, S., et al.: A cloud 3d dataset and application-specific learned image compression in cloud 3d. In: European Conference on Computer Vision, pp. 268\u2013284. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-19839-7_16"},{"key":"41_CR22","doi-asserted-by":"crossref","unstructured":"Liu, T., He, S., et al: A benchmarking framework for interactive 3d applications in the cloud. In: MICRO, pp. 881\u2013894. IEEE (2020)","DOI":"10.1109\/MICRO50266.2020.00076"},{"key":"41_CR23","doi-asserted-by":"crossref","unstructured":"Lohn, A., Knack, A., Burke, A., et al: Autonomous cyber defence: a roadmap from lab to ops. In: Center for Emerging Technology and Security (2023)","DOI":"10.51593\/2022CA007"},{"key":"41_CR24","unstructured":"TTCP CAGE Challenge 3. https:\/\/github.com\/cage-challenge\/cage-challenge-3. Accessed 10 Apr 2024"},{"key":"41_CR25","unstructured":"TTCP CAGE Challenge 4. https:\/\/github.com\/cage-challenge\/cage-challenge-4. Accessed 10 Apr 2024"},{"key":"41_CR26","doi-asserted-by":"crossref","unstructured":"Oliehoek, F.A.: Decentralized pomdps. In: Wiering, M., van Otterlo, M. (eds) Reinforcement Learning, pp. 471\u2013503, Spinger, Heidelberg (2012)","DOI":"10.1007\/978-3-642-27645-3_15"},{"key":"41_CR27","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"41_CR28","doi-asserted-by":"crossref","unstructured":"Tan, M.: Multi-agent reinforcement learning: independent vs. cooperative agents. In: ICML, pp. 330\u2013337. Morgan Kaufmann Publication, San Mateo (1993)","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"41_CR29","unstructured":"Sunehag, P., Lever, G., Gruslys, A., et al.: Value-decomposition networks for cooperative multi-agent learning based on team reward. In: AAMAS, pp. 2085\u20132087. Richland (2018)"},{"key":"41_CR30","unstructured":"Rashid, T., Samvelyan, M., De Witt, C.S., et al.: QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. In: JMLR, pp. 1\u201351 (2020)"},{"key":"41_CR31","unstructured":"Cyberbattlesim Project Document and Source Code. https:\/\/github.com\/microsoft\/CyberBattleSim. Accessed 10 Apr 2024"},{"key":"41_CR32","unstructured":"Baillie, C., Standen, M., Schwartz, J., et al.: Cyborg: an autonomous cyber operations research gym. arXiv preprint arXiv:2002.10667 (2020)"},{"key":"41_CR33","unstructured":"Standen, M., Lucas, M., Bowman, D., et al.: Cyborg: a gym for the development of autonomous cyber agents. arXiv preprint arXiv:2108.09118 (2021)"},{"key":"41_CR34","unstructured":"Jaromir, J., Tomas, P., Viliam, L.: NASimEmu: network attack simulator & emulator for training agents generalizing to novel scenarios. arXiv preprint arXiv:2305.17246 (2023)"},{"key":"41_CR35","unstructured":"Li, L., Fayad, R., Taylor, A.: Cygil: a cyber gym for training autonomous agents over emulated network systems. arXiv preprint arXiv:2109.03331 (2021)"},{"key":"41_CR36","unstructured":"Mitre ATT&CK Knowledge Base. https:\/\/attack.mitre.org\/. Accessed 10 Apr 2024"},{"key":"41_CR37","doi-asserted-by":"crossref","unstructured":"Nguyen, T.T., Reddi, V.J. Deep reinforcement learning for cyber security. In: TNNLS, pp. 3779\u20133795. IEEE (2021)","DOI":"10.1109\/TNNLS.2021.3121870"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5581-3_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T19:20:46Z","timestamp":1722540046000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5581-3_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819755806","9789819755813"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5581-3_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}