{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T01:24:00Z","timestamp":1752283440725,"version":"3.40.3"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031263682"},{"type":"electronic","value":"9783031263699"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-26369-9_6","type":"book-chapter","created":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T12:43:17Z","timestamp":1675860197000},"page":"107-126","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Robust Moving Target Defense Against Unknown Attacks: A Meta-reinforcement Learning Approach"],"prefix":"10.1007","author":[{"given":"Henger","family":"Li","sequence":"first","affiliation":[]},{"given":"Zizhan","family":"Zheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,9]]},"reference":[{"key":"6_CR1","series-title":"Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1007\/978-3-642-36883-7_19","volume-title":"Security and Privacy in Communication Networks","author":"E Al-Shaer","year":"2013","unstructured":"Al-Shaer, E., Duan, Q., Jafarian, J.H.: Random host mutation for moving target defense. In: Keromytis, A.D., Di Pietro, R. (eds.) SecureComm 2012. LNICST, vol. 106, pp. 310\u2013327. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-36883-7_19"},{"doi-asserted-by":"crossref","unstructured":"Allen, L., Heriyanto, T., Ali, S.: Kali Linux-Assuring Security by Penetration Testing. Packt Publishing Ltd. (2014)","key":"6_CR2","DOI":"10.1016\/S1353-4858(14)70077-7"},{"unstructured":"Basar, T.: Lecture notes on non-cooperative game theory (2010). https:\/\/www.hamilton.ie\/ollie\/Downloads\/Game.pdf","key":"6_CR3"},{"doi-asserted-by":"crossref","unstructured":"Ba\u015far, T., Olsder, G.J.: Dynamic Noncooperative Game Theory. SIAM (1998)","key":"6_CR4","DOI":"10.1137\/1.9781611971132"},{"unstructured":"Booth, H., Rike, D., Witte, G.A., et al.: The national vulnerability database (NVD): overview (2013)","key":"6_CR5"},{"unstructured":"Bowers, K.D., Dijk, M.E.V., Juels, A., Oprea, A.M., Rivest, R.L., Triandopoulos, N.: Graph-based approach to deterring persistent security threats. US Patent 8813234 (2014)","key":"6_CR6"},{"unstructured":"Brockman, G., et al.: OpenAI gym. ArXiv abs\/1606.01540 (2016)","key":"6_CR7"},{"issue":"1","key":"6_CR8","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1109\/COMST.2019.2963791","volume":"22","author":"JH Cho","year":"2020","unstructured":"Cho, J.H., et al.: Toward proactive, adaptive defense: a survey on moving target defense. IEEE Commun. Surv. Tutor. 22(1), 709\u2013745 (2020)","journal-title":"IEEE Commun. Surv. Tutor."},{"unstructured":"Derman, E., Mannor, S.: Distributional robustness and regularization in reinforcement learning. In: The Theoretical Foundations of Reinforcement Learning Workshop at ICML 2020 (2020)","key":"6_CR9"},{"unstructured":"Duan, Y., Schulman, J., Chen, X., Bartlett, P.L., Sutskever, I., Abbeel, P.: RL$$^2$$: fast reinforcement learning via slow reinforcement learning. arXiv preprint arXiv:1611.02779 (2016)","key":"6_CR10"},{"doi-asserted-by":"crossref","unstructured":"Eldosouky, A., Saad, W., Niyato, D.: Single controller stochastic games for optimized moving target defense. In: IEEE International Conference on Communications (ICC) (2016)","key":"6_CR11","DOI":"10.1109\/ICC.2016.7510985"},{"unstructured":"Fallah, A., Mokhtari, A., Ozdaglar, A.: Generalization of model-agnostic meta-learning algorithms: recurring and unseen tasks. In: NeurIPS (2021)","key":"6_CR12"},{"key":"6_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/978-3-319-68711-7_17","volume-title":"Decision and Game Theory for Security","author":"X Feng","year":"2017","unstructured":"Feng, X., Zheng, Z., Mohapatra, P., Cansever, D.: A Stackelberg game and Markov modeling of moving target defense. In: Rass, S., An, B., Kiekintveld, C., Fang, F., Schauer, S. (eds.) GameSec 2017. LNCS, vol. 10575, pp. 315\u2013335. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-68711-7_17"},{"unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning (ICML), pp. 1126\u20131135 (2017)","key":"6_CR14"},{"unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning (ICML), pp. 1587\u20131596 (2018)","key":"6_CR15"},{"issue":"5\u20136","key":"6_CR16","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1561\/2200000049","volume":"8","author":"M Ghavamzadeh","year":"2015","unstructured":"Ghavamzadeh, M., Mannor, S., Pineau, J., Tamar, A.: Bayesian reinforcement learning: a survey. Found. Trends Mach. Learn. 8(5\u20136), 359\u2013492 (2015)","journal-title":"Found. Trends Mach. Learn."},{"key":"6_CR17","first-page":"1039","volume":"4","author":"J Hu","year":"2003","unstructured":"Hu, J., Wellman, M.P.: Nash Q-learning for general-sum stochastic games. J. Mach. Learn. Res. 4, 1039\u20131069 (2003)","journal-title":"J. Mach. Learn. Res."},{"doi-asserted-by":"crossref","unstructured":"Huang, P., Xu, M., Fang, F., Zhao, D.: Robust reinforcement learning as a Stackelberg game via adaptively-regularized adversarial training. arXiv preprint arXiv:2202.09514 (2022)","key":"6_CR18","DOI":"10.24963\/ijcai.2022\/430"},{"key":"6_CR19","series-title":"Advances in Information Security","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/978-1-4614-0977-9_4","volume-title":"Moving Target Defense","author":"T Jackson","year":"2011","unstructured":"Jackson, T., et al.: Compiler-generated software diversity. In: Jajodia, S., Ghosh, A., Swarup, V., Wang, C., Wang, X. (eds.) Moving Target Defense. Advances in Information Security, vol. 54, pp. 77\u201398. Springer, New York (2011). https:\/\/doi.org\/10.1007\/978-1-4614-0977-9_4"},{"doi-asserted-by":"crossref","unstructured":"Jafarian, J.H., Al-Shaer, E., Duan, Q.: OpenFlow random host mutation: transparent moving target defense using software defined networking. In: Proceedings of the First Workshop on Hot Topics in Software Defined Networks (HotSDN), pp. 127\u2013132 (2012)","key":"6_CR20","DOI":"10.1145\/2342441.2342467"},{"key":"6_CR21","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-0977-9","volume-title":"Moving Target Defense: Creating Asymmetric Uncertainty for Cyber Threats","author":"S Jajodia","year":"2011","unstructured":"Jajodia, S., Ghosh, A.K., Swarup, V., Wang, C., Wang, X.S.: Moving Target Defense: Creating Asymmetric Uncertainty for Cyber Threats, vol. 54. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-1-4614-0977-9"},{"issue":"2","key":"6_CR22","first-page":"105","volume":"2","author":"V K\u00f6n\u00f6nen","year":"2004","unstructured":"K\u00f6n\u00f6nen, V.: Asymmetric multiagent reinforcement learning. Web Intell. Agent Syst. Int. J. (WIAS) 2(2), 105\u2013121 (2004)","journal-title":"Web Intell. Agent Syst. Int. J. (WIAS)"},{"doi-asserted-by":"crossref","unstructured":"Li, H., Shen, W., Zheng, Z.: Spatial-temporal moving target defense: a Markov Stackelberg game model. In: International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS) (2020)","key":"6_CR23","DOI":"10.1109\/MILCOM47813.2019.9020963"},{"doi-asserted-by":"crossref","unstructured":"Li, H., Zheng, Z.: Optimal timing of moving target defense: a Stackelberg game model. In: IEEE Military Communications Conference (MILCOM). IEEE (2019)","key":"6_CR24","DOI":"10.1109\/MILCOM47813.2019.9020963"},{"doi-asserted-by":"crossref","unstructured":"Luo, Y.B., Wang, B.S., Wang, X.F., Hu, X.F., Cai, G.L., Sun, H.: RPAH: random port and address hopping for thwarting internal and external adversaries. In: 2015 IEEE Trustcom\/BigDataSE\/ISPA, vol. 1, pp. 263\u2013270. IEEE (2015)","key":"6_CR25","DOI":"10.1109\/Trustcom.2015.383"},{"issue":"6","key":"6_CR26","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1109\/MSP.2006.145","volume":"4","author":"P Mell","year":"2006","unstructured":"Mell, P., Scarfone, K., Romanosky, S.: Common vulnerability scoring system. IEEE Secur. Priv. 4(6), 85\u201389 (2006)","journal-title":"IEEE Secur. Priv."},{"unstructured":"Nichol, A., Achiam, J., Schulman, J.: On first-order meta-learning algorithms. arXiv preprint arXiv:1803.02999 (2018)","key":"6_CR27"},{"unstructured":"Paruchuri, P., Pearce, J.P., Marecki, J., Tambe, M., Ordonez, F., Kraus, S.: Playing games for security: an efficient exact algorithm for solving Bayesian Stackelberg games. In: Proceedings of the 7th International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS), pp. 895\u2013902 (2008)","key":"6_CR28"},{"unstructured":"Paulin, A.: Secure SQL server-enabling secure access to remote relational data. arXiv preprint arXiv:1201.1081 (2012)","key":"6_CR29"},{"doi-asserted-by":"crossref","unstructured":"Peng, W., Li, F., Huang, C.T., Zou, X.: A moving-target defense strategy for cloud-based services with heterogeneous and dynamic attack surfaces. In: International Conference on Communications (ICC), pp. 804\u2013809. IEEE (2014)","key":"6_CR30","DOI":"10.1109\/ICC.2014.6883418"},{"unstructured":"Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-baselines3: Reliable reinforcement learning implementations. J. Mach. Learn. Res. (2021)","key":"6_CR31"},{"doi-asserted-by":"crossref","unstructured":"Saputro, N., Tonyali, S., Aydeger, A., Akkaya, K., Rahman, M.A., Uluagac, S.: A review of moving target defense mechanisms for internet of things applications. Model. Design Secure Internet Things 563\u2013614 (2020)","key":"6_CR32","DOI":"10.1002\/9781119593386.ch24"},{"unstructured":"Sengupta, S., Kambhampati, S.: Multi-agent reinforcement learning in bayesian Stackelberg Markov games for adaptive moving target defense. arXiv preprint arXiv:2007.10457 (2020)","key":"6_CR33"},{"unstructured":"Sengupta, S., et al.: A game theoretic approach to strategy generation for moving target defense in web applications. In: International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), pp. 178\u2013186 (2017)","key":"6_CR34"},{"doi-asserted-by":"crossref","unstructured":"Sharma, D.P., Kim, D.S., Yoon, S., Lim, H., Cho, J.H., Moore, T.J.: FRVM: flexible random virtual IP multiplexing in software-defined networks. In: IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom), pp. 579\u2013587. IEEE (2018)","key":"6_CR35","DOI":"10.1109\/TrustCom\/BigDataSE.2018.00088"},{"issue":"1","key":"6_CR36","first-page":"19","volume":"1","author":"A Sinha","year":"2015","unstructured":"Sinha, A., Nguyen, T.H., Kar, D., Brown, M., Tambe, M., Jiang, A.X.: From physical security to cybersecurity. J. Cybersecur. 1(1), 19\u201335 (2015)","journal-title":"J. Cybersecur."},{"unstructured":"von Stengel, B., Zamir, S.: Leadership with commitment to mixed strategies. CDAM Research Report LSE-CDAM-2004-01 (2004)","key":"6_CR37"},{"doi-asserted-by":"crossref","unstructured":"Taguinod, M., Doup\u00e9, A., Zhao, Z., Ahn, G.J.: Toward a moving target defense for web applications. In: 2015 IEEE International Conference on Information Reuse and Integration, pp. 510\u2013517. IEEE (2015)","key":"6_CR38","DOI":"10.1109\/IRI.2015.84"},{"doi-asserted-by":"crossref","unstructured":"Thomas, S., Williams, L.: Using automated fix generation to secure SQL statements. In: International Workshop on Software Engineering for Secure Systems (SESS). IEEE (2007)","key":"6_CR39","DOI":"10.1109\/SESS.2007.12"},{"doi-asserted-by":"crossref","unstructured":"Thompson, M., Evans, N., Kisekka, V.: Multiple OS rotational environment an implemented moving target defense. In: The 7th International Symposium on Resilient Control Systems (ISRCS), pp. 1\u20136. IEEE (2014)","key":"6_CR40","DOI":"10.1109\/ISRCS.2014.6900086"},{"unstructured":"Vorobeychik, Y., Singh, S.: Computing Stackelberg equilibria in discounted stochastic games (corrected version). In: Twenty-Sixth Conference on Artificial Intelligence (AAAI) (2012)","key":"6_CR41"},{"unstructured":"Vu, Q.L., et al.: Stackelberg policy gradient: evaluating the performance of leaders and followers. In: ICLR 2022 Workshop on Gamification and Multiagent Solutions (2022)","key":"6_CR42"},{"unstructured":"Wang, J.X., et al.: Learning to reinforcement learn. arXiv preprint arXiv:1611.05763 (2016)","key":"6_CR43"},{"unstructured":"Weng, L.: Meta-learning: learning to learn fast. lilianweng.github.io (2018). https:\/\/lilianweng.github.io\/posts\/2018-11-30-meta-learning\/","key":"6_CR44"},{"unstructured":"Xie, Q., Chen, Y., Wang, Z., Yang, Z.: Learning zero-sum simultaneous-move Markov games using function approximation and correlated equilibrium. In: COLT (2020)","key":"6_CR45"},{"key":"6_CR46","series-title":"IFIP Advances in Information and Communication Technology","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1007\/978-3-642-30436-1_32","volume-title":"Information Security and Privacy Research","author":"Y Zhang","year":"2012","unstructured":"Zhang, Y., Li, M., Bai, K., Yu, M., Zang, W.: Incentive compatible moving target defense against VM-colocation attacks in clouds. In: Gritzalis, D., Furnell, S., Theoharidou, M. (eds.) SEC 2012. IAICT, vol. 376, pp. 388\u2013399. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-30436-1_32"}],"container-title":["Lecture Notes in Computer Science","Decision and Game Theory for Security"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26369-9_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T13:05:47Z","timestamp":1675861547000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26369-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031263682","9783031263699"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26369-9_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"9 February 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"GameSec","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Decision and Game Theory for Security","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"PIttsburgh, PA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"gamesec2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.gamesec-conf.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"39","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"15","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"38% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}