{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:03:27Z","timestamp":1750309407617,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T00:00:00Z","timestamp":1698364800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,27]]},"DOI":"10.1145\/3650215.3650293","type":"proceedings-article","created":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T22:11:20Z","timestamp":1713305480000},"page":"442-448","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Research on path planning algorithm of partially observable penetration test based on reinforcement learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0195-8178","authenticated-orcid":false,"given":"Qinrui","family":"Sun","sequence":"first","affiliation":[{"name":"China Aerospace Academy of Systems Science and Engineering, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9889-2101","authenticated-orcid":false,"given":"Hui","family":"Ge","sequence":"additional","affiliation":[{"name":"China Aerospace Academy of Systems Science and Engineering, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3967-3033","authenticated-orcid":false,"given":"Xiao","family":"Jin","sequence":"additional","affiliation":[{"name":"China Aerospace Academy of Systems Science and Engineering, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,4,16]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Attack trees [J]. Dr. Dobb's journal","author":"Schneier B.","year":"1999","unstructured":"Schneier B. Attack trees [J]. Dr. Dobb's journal, 1999, 24(12): 21-29."},{"key":"e_1_3_2_1_2_1","volume-title":"Using attack trees to identify malicious attacks from authorized insiders[C]\/\/European Symposium on Research in Computer Security","author":"Ray I","year":"2005","unstructured":"Ray I, Poolsapassit N. Using attack trees to identify malicious attacks from authorized insiders[C]\/\/European Symposium on Research in Computer Security. Springer, Berlin, Heidelberg, 2005, 231-246."},{"key":"e_1_3_2_1_3_1","volume-title":"A graph-based system for network-vulnerability analysis[C]\/\/Proceedings of the 1998 workshop on New security paradigms","author":"Phillips C","year":"1998","unstructured":"Phillips C, Swiler L P. A graph-based system for network-vulnerability analysis[C]\/\/Proceedings of the 1998 workshop on New security paradigms. 1998, 71-79."},{"key":"e_1_3_2_1_4_1","volume-title":"Reinforcement learning: An introduction [M]","author":"Sutton R S","year":"2018","unstructured":"Sutton R S, Barto A G. Reinforcement learning: An introduction [M]. MIT press, 2018."},{"key":"e_1_3_2_1_5_1","first-page":"590","volume-title":"IEEE","author":"Nguyen H","year":"2019","unstructured":"Nguyen H, La H. Review of deep reinforcement learning for robot manipulation[C]\/\/2019 Third IEEE International Conference on Robotic Computing (IRC). IEEE, 2019, 590-595."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.add4679"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543846"},{"key":"e_1_3_2_1_9_1","volume-title":"Optimizing risk-based breast cancer screening policies with reinforcement learning [J]. Nature medicine","author":"Yala A","year":"2022","unstructured":"Yala A, Mikhael P G, Lehman C, Optimizing risk-based breast cancer screening policies with reinforcement learning [J]. Nature medicine, 2022, 28(1): 136-143."},{"key":"e_1_3_2_1_10_1","volume-title":"Autonomous penetration testing using reinforcement learning [J]. arXiv preprint arXiv:1905. 05965","author":"Schwartz J","year":"2019","unstructured":"Schwartz J, Kurniawati H. Autonomous penetration testing using reinforcement learning [J]. arXiv preprint arXiv:1905. 05965, 2019."},{"key":"e_1_3_2_1_11_1","volume-title":"The Proposal of Double Agent Architecture using Actor-critic Algorithm for Penetration Testing[C]\/\/ICISSP","author":"Nguyen H V","year":"2021","unstructured":"Nguyen H V, Teerakanok S, Inomata A, The Proposal of Double Agent Architecture using Actor-critic Algorithm for Penetration Testing[C]\/\/ICISSP. 2021, 440-449."},{"key":"e_1_3_2_1_12_1","volume-title":"Incorporating defender's behaviour in autonomous penetration testing[C]\/\/Proceedings of the International Conference on Automated Planning and Scheduling","author":"Schwartz J","year":"2020","unstructured":"Schwartz J, Kurniawati H, El-Mahassni E. Pomdp+ information-decay: Incorporating defender's behaviour in autonomous penetration testing[C]\/\/Proceedings of the International Conference on Automated Planning and Scheduling. 2020, 30: 235-243."},{"issue":"5","key":"e_1_3_2_1_13_1","volume":"7","author":"Gao W.","year":"2022","unstructured":"Gao, W., Zhou, T., Zhao, Z., Method of Network Attack Path Planning Based on Deep Reinforcement Learning[J]. Journal of Cyber Security, 2022, 7(5).","journal-title":"Journal of Cyber Security"},{"issue":"07","key":"e_1_3_2_1_14_1","first-page":"40","volume":"48","author":"Zhou S.","year":"2021","unstructured":"Zhou, S., Liu, J., Zhong, X., Intelligent Penetration Testing Path Discovery Based on Deep Reinforcement Learning [J]. Computer Science, 2021, 48(07):40-46.","journal-title":"Computer Science"},{"key":"e_1_3_2_1_15_1","first-page":"476","volume-title":"IEEE","author":"Wang P","year":"2022","unstructured":"Wang P, Liu J, Zhong X, DUSC-DQN: An Improved Deep Q-Network for Intelligent Penetration Testing Path Design[C]\/\/2022 7th International Conference on Computer and Communication Systems (ICCCS). IEEE, 2022, 476-480."},{"key":"e_1_3_2_1_16_1","volume-title":"Human-level control through deep reinforcement learning[J]. nature","author":"Mnih V","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Human-level control through deep reinforcement learning[J]. nature, 2015, 518(7540): 529-533."},{"key":"e_1_3_2_1_17_1","volume-title":"Deep recurrent q-learning for partially observable mdps[C]\/\/2015 aaai fall symposium series","author":"Hausknecht M","year":"2015","unstructured":"Hausknecht M, Stone P. Deep recurrent q-learning for partially observable mdps[C]\/\/2015 aaai fall symposium series. 2015."},{"key":"e_1_3_2_1_18_1","volume-title":"Learning from delayed rewards [J]","author":"Watkins C J C H","year":"1989","unstructured":"Watkins C J C H. Learning from delayed rewards [J]. 1989."},{"key":"e_1_3_2_1_19_1","volume-title":"Deep reinforcement learning with double q-learning[C]\/\/Proceedings of the AAAI conference on artificial intelligence","author":"Van Hasselt H","year":"2016","unstructured":"Van Hasselt H, Guez A, Silver D. Deep reinforcement learning with double q-learning[C]\/\/Proceedings of the AAAI conference on artificial intelligence. 2016, 30(1)."},{"key":"e_1_3_2_1_20_1","volume-title":"Prioritized experience replay [J]. arXiv preprint arXiv:1511.05952","author":"Schaul T","year":"2015","unstructured":"Schaul T, Quan J, Antonoglou I, Prioritized experience replay [J]. arXiv preprint arXiv:1511.05952, 2015."}],"event":{"name":"ICMLCA 2023: 2023 4th International Conference on Machine Learning and Computer Application","acronym":"ICMLCA 2023","location":"Hangzhou China"},"container-title":["2023 4th International Conference on Machine Learning and Computer Application"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650215.3650293","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3650215.3650293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:04Z","timestamp":1750294684000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650215.3650293"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,27]]},"references-count":20,"alternative-id":["10.1145\/3650215.3650293","10.1145\/3650215"],"URL":"https:\/\/doi.org\/10.1145\/3650215.3650293","relation":{},"subject":[],"published":{"date-parts":[[2023,10,27]]},"assertion":[{"value":"2024-04-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}