{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T16:46:15Z","timestamp":1791996375023,"version":"4.4.0"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,13]]},"DOI":"10.1145\/3733799.3762965","type":"proceedings-article","created":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T11:38:49Z","timestamp":1767094729000},"page":"40-51","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Online Incident Response Planning under Model Misspecification through Bayesian Learning and Belief Quantization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1773-8354","authenticated-orcid":false,"given":"Kim","family":"Hammar","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8966-7239","authenticated-orcid":false,"given":"Tao","family":"Li","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,30]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-29587-9"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511760778"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72709-5_1"},{"key":"e_1_3_3_2_5_2","volume-title":"Computer Security Threat Monitoring and Surveillance","author":"Anderson James\u00a0P.","year":"1980","unstructured":"James\u00a0P. Anderson. 1980. Computer Security Threat Monitoring and Surveillance. Technical Report Contract 79F26400. James P. Anderson Co., Fort Washington, PA. Prepared for the United States Air Force."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3560830.3563732"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/NCS.2018.00007"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3605764.3623916"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","unstructured":"Yahuza Bello and Ahmed\u00a0Refaey Hussein. 2024. Dynamic Policy Decision\/Enforcement Security Zoning Through Stochastic Games and Meta Learning. IEEE Transactions on Network and Service Management (2024) 1\u20131. 10.1109\/TNSM.2024.3481662","DOI":"10.1109\/TNSM.2024.3481662"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Robert\u00a0H. Berk. 1966. Limiting Behavior of Posterior Distributions when the Model is Incorrect. The Annals of Mathematical Statistics 37 1 (1966) 51 \u2013 58. 10.1214\/aoms\/1177699597","DOI":"10.1214\/aoms\/1177699597"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Dimitri Bertsekas. 2019. Feature-based aggregation and deep reinforcement learning: A survey and some new implementations. IEEE\/CAA Journal of Automatica Sinica 6 1 (2019) 1\u201331. 10.1109\/JAS.2018.7511249","DOI":"10.1109\/JAS.2018.7511249"},{"key":"e_1_3_3_2_12_2","volume-title":"Reinforcement learning and optimal control","author":"Bertsekas Dimitri","year":"2019","unstructured":"Dimitri Bertsekas. 2019. Reinforcement learning and optimal control. Athena Scientific."},{"key":"e_1_3_3_2_13_2","volume-title":"A Course in Reinforcement Learning","author":"Bertsekas Dimitri","year":"2025","unstructured":"Dimitri Bertsekas. 2025. A Course in Reinforcement Learning. Athena Scientific. 2nd edition."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45598-1_12"},{"key":"e_1_3_3_2_15_2","volume-title":"AAAI-22 Workshop on Artificial Intelligence for Cyber Security (AICS)","year":"2022","unstructured":"CAGE. 2022. TTCP CAGE Challenge 2. In AAAI-22 Workshop on Artificial Intelligence for Cyber Security (AICS)."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3689932.3694770"},{"key":"e_1_3_3_2_17_2","unstructured":"Sebasti\u00e1n\u00a0R. Castro Roberto Campbell Nancy Lau Octavio Villalobos Jiaqi Duan and Alvaro\u00a0A. Cardenas. 2025. Large Language Models are Autonomous Cyber Defenders. arxiv:https:\/\/arXiv.org\/abs\/2505.04843\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2505.04843"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/infocomwkshps57453.2023.10225816"},{"key":"e_1_3_3_2_19_2","first-page":"1","volume-title":"In Proceedings of the 23rd National Information Systems Secuity Conference","author":"Georgia James\u00a0Cannady","year":"2000","unstructured":"James\u00a0Cannady Georgia. 2000. Next Generation Intrusion Detection: Autonomous Reinforcement Learning of Network Attacks. In In Proceedings of the 23rd National Information Systems Secuity Conference. 1\u201312."},{"key":"e_1_3_3_2_20_2","unstructured":"Kim Hammar Tansu Alpcan and Emil\u00a0C. Lupu. 2025. Incident Response Planning Using a Lightweight Large Language Model with Reduced Hallucination. arxiv:https:\/\/arXiv.org\/abs\/2508.05188\u00a0[cs.CR] https:\/\/arxiv.org\/abs\/2508.05188"},{"key":"e_1_3_3_2_21_2","unstructured":"Kim Hammar Neil Dhir and Rolf Stadler. 2024. Optimal Defender Strategies for CAGE-2 using Causal Modeling and Tree Search. arxiv:https:\/\/arXiv.org\/abs\/2407.11070\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2407.11070"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","unstructured":"Kim Hammar Tao Li Rolf Stadler and Quanyan Zhu. 2025. Adaptive Security Response Strategies Through Conjectural Online Learning. IEEE Transactions on Information Forensics and Security 20 (2025) 4055\u20134070. 10.1109\/TIFS.2025.3558600","DOI":"10.1109\/TIFS.2025.3558600"},{"key":"e_1_3_3_2_23_2","unstructured":"Kim Hammar Yuchao Li Tansu Alpcan Emil\u00a0C. Lupu and Dimitri Bertsekas. 2025. Adaptive network security policies via belief aggregation and rollout. https:\/\/arxiv.org\/abs\/2507.15163."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN58291.2024.00042"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","unstructured":"Yi Han Tansu Alpcan Jeffrey Chan Christopher Leckie and Benjamin I.\u00a0P. Rubinstein. 2016. A Game Theoretical Approach to Defend Against Co-Resident Attacks in Cloud Computing: Preventing Co-Residence Using Semi-Supervised Learning. IEEE Transactions on Information Forensics and Security 11 3 (2016) 556\u2013570. 10.1109\/TIFS.2015.2505680","DOI":"10.1109\/TIFS.2015.2505680"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01554-1_9"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3605764.3623986"},{"key":"e_1_3_3_2_28_2","unstructured":"Zequan Huang Jacques Robin Nicolas Herbaut Nourh\u00e8ne\u00a0Ben Rabah and B\u00e9n\u00e9dicte\u00a0Le Grand. 2025. Toward an Intent-Based and Ontology-Driven Autonomic Security Response in Security Orchestration Automation and Response. arxiv:https:\/\/arXiv.org\/abs\/2507.12061\u00a0[cs.CR] https:\/\/arxiv.org\/abs\/2507.12061"},{"key":"e_1_3_3_2_29_2","unstructured":"Eric\u00a0M Hutchins Michael\u00a0J Cloppert Rohan\u00a0M Amin et\u00a0al. 2011. Intelligence-driven computer network defense informed by analysis of adversary campaigns and intrusion kill chains. Leading Issues in Information Warfare & Security Research 1 1 (2011) 80."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN.2016.7568529"},{"key":"e_1_3_3_2_31_2","volume-title":"Cost of a Data Breach Report 2024","author":"Security IBM","year":"2024","unstructured":"IBM Security and Ponemon Institute. 2024. Cost of a Data Breach Report 2024. Technical Report\u00a019. IBM, Cambridge, MA. Based on breaches at 524 organizations across 17 industries in 16 countries between March 2023 and February 2024.."},{"key":"e_1_3_3_2_32_2","unstructured":"C.\u00a0T. Ionescu-Tulcea. 1949. Mesures dans les espaces produits. Atti della Accademia Nazionale dei Lincei Rendiconti Classe di Scienze Fisiche Matematiche e Naturali 7 (1949) 208\u2013211."},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","unstructured":"Michael Kearns and Satinder Singh. 2002. Near-Optimal Reinforcement Learning in Polynomial Time. Machine Learning 49 2 (01 Nov 2002) 209\u2013232. 10.1023\/A:1017984413808","DOI":"10.1023\/A:1017984413808"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781316471104"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","unstructured":"Mehmet\u00a0Necip Kurt Oyetunji Ogundijo Chong Li and Xiaodong Wang. 2019. Online Cyber-Attack Detection in Smart Grid: A Reinforcement Learning Approach. IEEE Transactions on Smart Grid 10 5 (2019) 5174\u20135185. 10.1109\/TSG.2018.2878570","DOI":"10.1109\/TSG.2018.2878570"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC56724.2024.10886479"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-53510-9_2"},{"key":"e_1_3_3_2_38_2","unstructured":"Tao Li Ya-Ting Yang Yunian Pan and Quanyan Zhu. 2025. From Texts to Shields: Convergence of Large Language Models and Cybersecurity. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.00841 (2025). arXiv:https:\/\/arXiv.org\/abs\/2505.00841"},{"key":"e_1_3_3_2_39_2","volume-title":"Foundations of Cyber Deception","author":"Li Tao","year":"2025","unstructured":"Tao Li and Quanyan Zhu. 2025. Symbiotic game and foundation models for cyber deception operations in strategic cyber warfare. In Foundations of Cyber Deception. Springer Cham, Cham, Switzerland. [Online] Available at https:\/\/arxiv.org\/pdf\/2403.10570."},{"key":"e_1_3_3_2_40_2","unstructured":"Yuchao Li Kim Hammar and Dimitri Bertsekas. 2025. Feature-Based Belief Aggregation for Partially Observable Markovian Decision Problems. https:\/\/arxiv.org\/abs\/2507.04646."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","unstructured":"Erik Miehling Mohammad Rasouli and Demosthenis Teneketzis. 2018. A POMDP Approach to the Dynamic Defense of Large-Scale Cyber Networks. IEEE Transactions on Information Forensics and Security 13 10 (2018). 10.1109\/TIFS.2018.2819967","DOI":"10.1109\/TIFS.2018.2819967"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","unstructured":"Shana Moothedath Dinuka Sahabandu Joey Allen Andrew Clark Linda Bushnell Wenke Lee and Radha Poovendran. 2020. A Game-Theoretic Approach for Dynamic Information Flow Tracking to Detect Multistage Advanced Persistent Threats. IEEE Trans. Automat. Control 65 12 (2020) 5248\u20135263. 10.1109\/TAC.2020.2976040","DOI":"10.1109\/TAC.2020.2976040"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","unstructured":"Thanh\u00a0Thi Nguyen and Vijay\u00a0Janapa Reddi. 2023. Deep Reinforcement Learning for Cyber Security. IEEE Transactions on Neural Networks and Learning Systems 34 8 (2023) 3779\u20133795. 10.1109\/TNNLS.2021.3121870","DOI":"10.1109\/TNNLS.2021.3121870"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","unstructured":"Trung\u00a0V. Phan and Thomas Bauschert. 2022. DeepAir: Deep Reinforcement Learning for Adaptive Intrusion Response in Software-Defined Networks. IEEE Transactions on Network and Service Management (2022) 1\u20131. 10.1109\/TNSM.2022.3158468","DOI":"10.1109\/TNSM.2022.3158468"},{"key":"e_1_3_3_2_45_2","unstructured":"Antonin Raffin Ashley Hill Adam Gleave Anssi Kanervisto Maximilian Ernestus and Noah Dormann. 2021. Stable-Baselines3: Reliable Reinforcement Learning Implementations. Journal of Machine Learning Research 22 268 (2021) 1\u20138. http:\/\/jmlr.org\/papers\/v22\/20-1364.html"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"crossref","unstructured":"Maria Rigaki Ond\u0159ej Luk\u00e1\u0161 Carlos\u00a0A. Catania and Sebastian Garcia. 2023. Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments. arxiv:https:\/\/arXiv.org\/abs\/2308.12086\u00a0[cs.CR]","DOI":"10.5220\/0012391800003636"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","unstructured":"Naci Saldi Serdar Y\u00fcksel and Tam\u00e1s Linder. 2017. On the Asymptotic Optimality of Finite Approximations to Markov Decision Processes with Borel Spaces. Math. Oper. Res. 42 4 (Nov. 2017) 945\u2013978. 10.1287\/moor.2016.0832","DOI":"10.1287\/moor.2016.0832"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00060"},{"key":"e_1_3_3_2_49_2","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. CoRR (2017). arxiv:https:\/\/arXiv.org\/abs\/1707.06347http:\/\/arxiv.org\/abs\/1707.06347 http:\/\/arxiv.org\/abs\/1707.06347."},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77949-0_15"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","unstructured":"David Silver et\u00a0al. 2016. Mastering the Game of Go with Deep Neural Networks and Tree Search. Nature 529 7587 (Jan. 2016) 484\u2013489. 10.1038\/nature16961","DOI":"10.1038\/nature16961"},{"key":"e_1_3_3_2_52_2","volume-title":"Advances in Neural Information Processing Systems","author":"Silver David","year":"2010","unstructured":"David Silver and Joel Veness. 2010. Monte-Carlo Planning in Large POMDPs. In Advances in Neural Information Processing Systems , Vol.\u00a023."},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517559"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","unstructured":"John\u00a0N. Tsitsiklis and Benjamin van Roy. 1996. Feature-based methods for large scale dynamic programming. Machine Learning 22 1 (01 Mar 1996) 59\u201394. 10.1007\/BF00114724","DOI":"10.1007\/BF00114724"},{"key":"e_1_3_3_2_55_2","unstructured":"Sanyam Vyas John Hannay Andrew Bolton and Professor\u00a0Pete Burnap. 2023. Automated Cyber Defence: A Review. arxiv:https:\/\/arXiv.org\/abs\/2303.04926\u00a0[cs.CR] https:\/\/arxiv.org\/abs\/2303.04926 code: https:\/\/github.com\/john-cardiff\/-cyborg-cage-2."},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","unstructured":"Stephen Walker and Nils\u00a0Lid Hjort. 2001. On Bayesian consistency. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 63 4 (2001) 811\u2013821. 10.1111\/1467-9868.00314","DOI":"10.1111\/1467-9868.00314"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","unstructured":"Zelin Wan Jin-Hee Cho Mu Zhu Ahmed\u00a0H. Anwar Charles\u00a0A. Kamhoua and Munindar\u00a0P. Singh. 2022. Foureye: Defensive Deception Against Advanced Persistent Threats via Hypergame Theory. IEEE Transactions on Network and Service Management 19 1 (2022) 112\u2013129. 10.1109\/TNSM.2021.3117698","DOI":"10.1109\/TNSM.2021.3117698"},{"key":"e_1_3_3_2_58_2","unstructured":"Wazuh Inc. 2022. Wazuh - The Open Source Security Platform. https:\/\/wazuh.com\/"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","unstructured":"Melody Wolk Andy Applebaum Camron Dennler Patrick Dwyer Marina Moskowitz Harold Nguyen Nicole Nichols Nicole Park Paul Rachwalski Frank Rau and Adrian Webster. 2022. Beyond CAGE: Investigating Generalization of Learned Autonomous Network Defense Policies. 10.48550\/ARXIV.2211.15557","DOI":"10.48550\/ARXIV.2211.15557"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/11538059_103"},{"key":"e_1_3_3_2_61_2","unstructured":"Huizhen Yu. 2006. Approximate solution methods for partially observable markov and semi-markov decision processes. Ph.\u00a0D. Dissertation. Massachusetts Institute of Technology USA. Advisor(s) Bertsekas Dimitri."},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.5555\/1036843.1036918"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","unstructured":"Lefeng Zhang Tianqing Zhu Farookh\u00a0Khadeer Hussain Dayong Ye and Wanlei Zhou. 2022. Defend to Defeat: Limiting Information Leakage in Defending against Advanced Persistent Threats. IEEE Transactions on Information Forensics and Security (2022) 1\u20131. 10.1109\/TIFS.2022.3229595","DOI":"10.1109\/TIFS.2022.3229595"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2009.5270307"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"publisher","unstructured":"Karl\u00a0Johan \u00c5str\u00f6m. 1965. Optimal control of Markov processes with incomplete state information. J. Math. Anal. Appl. 10 1 (1965) 174\u2013205. 10.1016\/0022-247X(65)90154-X","DOI":"10.1016\/0022-247X(65)90154-X"}],"event":{"name":"AISec '25: Proceedings of the 2025 Workshop on Artificial Intelligence and Security","location":"Taipei , Taiwan","acronym":"AISec '25","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"]},"container-title":["Proceedings of the 18th ACM Workshop on Artificial Intelligence and Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3733799.3762965","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T11:52:52Z","timestamp":1767095572000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3733799.3762965"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"references-count":64,"alternative-id":["10.1145\/3733799.3762965","10.1145\/3733799"],"URL":"https:\/\/doi.org\/10.1145\/3733799.3762965","relation":{},"subject":[],"published":{"date-parts":[[2025,10,13]]},"assertion":[{"value":"2025-12-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}