{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T05:45:44Z","timestamp":1776836744058,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-22-PECY-0008"],"award-info":[{"award-number":["ANR-22-PECY-0008"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,9,30]]},"DOI":"10.1145\/3678890.3678902","type":"proceedings-article","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T22:23:36Z","timestamp":1727648616000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Leveraging Deep Reinforcement Learning for Cyber-Attack Paths Prediction: Formulation, Generalization, and Evaluation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6989-2655","authenticated-orcid":false,"given":"Franco","family":"Terranova","sequence":"first","affiliation":[{"name":"Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3882-1560","authenticated-orcid":false,"given":"Abdelkader","family":"Lahmadi","sequence":"additional","affiliation":[{"name":"Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8474-0019","authenticated-orcid":false,"given":"Isabelle","family":"Chrisment","sequence":"additional","affiliation":[{"name":"Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, France"}]}],"member":"320","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-44257-0_7"},{"key":"e_1_3_2_1_2_1","unstructured":"Rishabh Agarwal Max Schwarzer Pablo\u00a0Samuel Castro Aaron Courville and Marc\u00a0G. Bellemare. 2022. Deep Reinforcement Learning at the Edge of the Statistical Precipice. arxiv:2108.13264\u00a0[cs.LG]"},{"key":"e_1_3_2_1_3_1","volume-title":"Optuna: A Next-generation Hyperparameter Optimization Framework. arxiv:1907.10902\u00a0[cs.LG]","author":"Akiba Takuya","year":"2019","unstructured":"Takuya Akiba, Shotaro Sano, Toshihiko Yanase, Takeru Ohta, and Masanori Koyama. 2019. Optuna: A Next-generation Hyperparameter Optimization Framework. arxiv:1907.10902\u00a0[cs.LG]"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560830.3563732"},{"key":"e_1_3_2_1_5_1","unstructured":"Callum Baillie Maxwell Standen Jonathon Schwartz Michael Docking David Bowman and Junae Kim. 2020. CybORG: An Autonomous Cyber Operations Research Gym. arxiv:2002.10667\u00a0[cs.CR]"},{"key":"e_1_3_2_1_6_1","unstructured":"Marc\u00a0G. Bellemare Will Dabney and R\u00e9mi Munos. 2017. A Distributional Perspective on Reinforcement Learning. arxiv:1707.06887\u00a0[cs.LG]"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2022.3183476"},{"key":"e_1_3_2_1_8_1","unstructured":"James Bergstra R\u00e9mi Bardenet Yoshua Bengio and Bal\u00e1zs K\u00e9gl. 2011. Algorithms for hyper-parameter optimization. In Advances in neural information processing systems Vol.\u00a024."},{"key":"e_1_3_2_1_9_1","unstructured":"Greg Brockman Vicki Cheung Ludwig Pettersson Jonas Schneider John Schulman Jie Tang and Wojciech Zaremba. 2016. OpenAI Gym. arxiv:1606.01540\u00a0[cs.LG]"},{"key":"e_1_3_2_1_10_1","unstructured":"C\u00e9dric Colas Olivier Sigaud and Pierre-Yves Oudeyer. 2018. How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments. arxiv:1806.08295\u00a0[cs.LG]"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Will Dabney Mark Rowland Marc\u00a0G. Bellemare and R\u00e9mi Munos. 2017. Distributional Reinforcement Learning with Quantile Regression. arxiv:1710.10044\u00a0[cs.AI]","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176344552"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.22042\/isecure.2015.3.2.3"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3433174.3433614"},{"key":"e_1_3_2_1_15_1","volume-title":"Catastrophic forgetting in connectionist networks. Trends in cognitive sciences 3, 4","author":"French M","year":"1999","unstructured":"Robert\u00a0M French. 1999. Catastrophic forgetting in connectionist networks. Trends in cognitive sciences 3, 4 (1999), 128\u2013135."},{"key":"e_1_3_2_1_16_1","volume-title":"Deep Learning","author":"Goodfellow Ian","unstructured":"Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT Press. http:\/\/www.deeplearningbook.org."},{"key":"e_1_3_2_1_17_1","volume-title":"Deep Learning","author":"Goodfellow Ian","unstructured":"Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT Press. http:\/\/www.deeplearningbook.org."},{"key":"e_1_3_2_1_18_1","unstructured":"Greenbone Networks GmbH. Year. OpenVAS - Open Vulnerability Assessment System. https:\/\/www.openvas.org\/"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2023.10272349"},{"key":"e_1_3_2_1_20_1","volume-title":"Neural Networks: A Comprehensive Foundation","author":"Haykin Simon","year":"1998","unstructured":"Simon Haykin. 1998. Neural Networks: A Comprehensive Foundation (2nd ed.). Prentice Hall PTR, USA.","edition":"2"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Peter Henderson Riashat Islam Philip Bachman Joelle Pineau Doina Precup and David Meger. 2019. Deep Reinforcement Learning that Matters. arxiv:1709.06560\u00a0[cs.LG]","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"e_1_3_2_1_22_1","volume-title":"Long short-term memory. Neural computation 9, 8","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735\u20131780."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSPW51379.2020.00010"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSPW51379.2020.00010"},{"key":"e_1_3_2_1_25_1","unstructured":"Lei Huang Jie Qin Yi Zhou Fan Zhu Li Liu and Ling Shao. 2020. Normalization Techniques in Training DNNs: Methodology Analysis and Application. arxiv:2009.12836\u00a0[cs.LG]"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/cplx.20001"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2871866"},{"key":"e_1_3_2_1_28_1","volume-title":"Continuous Univariate Distributions","volume":"2","author":"Johnson L.","unstructured":"Norman\u00a0L. Johnson, Samuel Kotz, and N. Balakrishnan. 1995. Continuous Univariate Distributions, Volume 2. Wiley."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3538969.3544431"},{"key":"e_1_3_2_1_31_1","unstructured":"Li Li Raed Fayad and Adrian Taylor. 2021. CyGIL: A Cyber Gym for Training Autonomous Agents over Emulated Network Systems. arxiv:2109.03331\u00a0[cs.CR]"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-04946-1"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.3390\/app12126186"},{"key":"e_1_3_2_1_34_1","unstructured":"Gordon Lyon. 2008. Nmap Network Scanning: The Official Nmap Project Guide to Network Discovery and Security Scanning. Insecure.Com LLC."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177730491"},{"key":"e_1_3_2_1_36_1","unstructured":"Volodymyr Mnih Adri\u00e0\u00a0Puigdom\u00e8nech Badia Mehdi Mirza Alex Graves Timothy\u00a0P. Lillicrap Tim Harley David Silver and Koray Kavukcuoglu. 2016. Asynchronous Methods for Deep Reinforcement Learning. arxiv:1602.01783\u00a0[cs.LG]"},{"key":"e_1_3_2_1_37_1","volume-title":"Human-level control through deep reinforcement learning. Nature 518, 7540","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2015. Human-level control through deep reinforcement learning. Nature 518, 7540 (2015), 529\u2013533."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Thomas\u00a0M. Moerland Joost Broekens Aske Plaat and Catholijn\u00a0M. Jonker. 2022. Model-based Reinforcement Learning: A Survey. arxiv:2006.16712\u00a0[cs.LG]","DOI":"10.1561\/9781638280576"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"James\u00a0R Norris. 1998. Markov Chains. Cambridge University Press.","DOI":"10.1017\/CBO9780511810633"},{"key":"e_1_3_2_1_40_1","volume-title":"MulVAL: A Logic-based Network Security Analyzer. In 14th USENIX Security Symposium (USENIX Security 05)","author":"Ou Xinming","year":"2005","unstructured":"Xinming Ou, Sudhakar Govindavajhala, and Andrew\u00a0W. Appel. 2005. MulVAL: A Logic-based Network Security Analyzer. In 14th USENIX Security Symposium (USENIX Security 05). USENIX Association, Baltimore, MD."},{"key":"e_1_3_2_1_41_1","unstructured":"Andrew Patterson Samuel Neumann Martha White and Adam White. 2023. Empirical Design in Reinforcement Learning. arxiv:2304.01315\u00a0[cs.LG]"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA55696.2022.00213"},{"key":"e_1_3_2_1_43_1","unstructured":"Marco Pleines Matthias Pallasch Frank Zimmer and Mike Preuss. 2022. Generalization Mayhems and Limits in Recurrent Proximal Policy Optimization. arxiv:2205.11104\u00a0[cs.LG]"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Martin\u00a0L. Puterman. 1994. Markov Decision Processes: Discrete Stochastic Dynamic Programming.","DOI":"10.1002\/9780470316887"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSAC.2004.7"},{"key":"e_1_3_2_1_46_1","first-page":"1","article-title":"Stable-Baselines3: Reliable Reinforcement Learning Implementations","volume":"22","author":"Raffin Antonin","year":"2021","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","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_47_1","volume-title":"Proceedings of the USENIX LISA \u201999 Conference. https:\/\/www.usenix.org\/conference\/lisa-99\/snort-lightweight-intrusion-detection-networks","author":"Roesch Martin","year":"1999","unstructured":"Martin Roesch. 1999. Snort - Lightweight Intrusion Detection for Networks. In Proceedings of the USENIX LISA \u201999 Conference. https:\/\/www.usenix.org\/conference\/lisa-99\/snort-lightweight-intrusion-detection-networks"},{"key":"e_1_3_2_1_48_1","unstructured":"John Schulman Sergey Levine Philipp Moritz Michael\u00a0I. Jordan and Pieter Abbeel. 2017. Trust Region Policy Optimization. arxiv:1502.05477\u00a0[cs.LG]"},{"key":"e_1_3_2_1_49_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. arxiv:1707.06347\u00a0[cs.LG]"},{"key":"e_1_3_2_1_50_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton S.","year":"2018","unstructured":"Richard\u00a0S. Sutton and Andrew\u00a0G. Barto. 2018. Reinforcement Learning: An Introduction (second ed.). The MIT Press."},{"key":"e_1_3_2_1_51_1","unstructured":"Microsoft Defender\u00a0Research Team.2021. CyberBattleSim. https:\/\/github.com\/microsoft\/cyberbattlesim. Created by Christian Seifert Michael Betser William Blum James Bono Kate Farris Emily Goren Justin Grana Kristian Holsheimer Brandon Marken Joshua Neil Nicole Nichols Jugal Parikh Haoran Wei.."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","unstructured":"Franco Terranova Abdelkader Lahmadi and Isabelle Chrisment. 2024. Code for the paper \"Leveraging Deep Reinforcement Learning for Cyber-Attack Paths Prediction: Formulation Generalization and Evaluation\". https:\/\/doi.org\/10.5281\/zenodo.12783985. https:\/\/doi.org\/10.5281\/zenodo.12783985","DOI":"10.5281\/zenodo.12783985"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","unstructured":"Franco Terranova Abdelkader Lahmadi and Isabelle Chrisment. 2024. Topologies Checkpoints and Configurations for the paper \"Leveraging Deep Reinforcement Learning for Cyber-Attack Paths Prediction: Formulation Generalization and Evaluation\". https:\/\/doi.org\/10.5281\/zenodo.12783622. https:\/\/doi.org\/10.5281\/zenodo.12783622","DOI":"10.5281\/zenodo.12783622"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.3390\/app13169467"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.3390\/app122010339"}],"event":{"name":"RAID '24: The 27th International Symposium on Research in Attacks, Intrusions and Defenses","location":"Padua Italy","acronym":"RAID '24"},"container-title":["The 27th International Symposium on Research in Attacks, Intrusions and Defenses"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3678890.3678902","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3678890.3678902","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:00Z","timestamp":1750295880000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3678890.3678902"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"references-count":55,"alternative-id":["10.1145\/3678890.3678902","10.1145\/3678890"],"URL":"https:\/\/doi.org\/10.1145\/3678890.3678902","relation":{},"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"2024-09-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}