{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:07:53Z","timestamp":1780636073641,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819699070","type":"print"},{"value":"9789819699087","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-9908-7_39","type":"book-chapter","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T16:26:43Z","timestamp":1753374403000},"page":"472-486","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Automated Penetration Testing Through Hierarchical PPO with Large Language Model Enhancement"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7679-6692","authenticated-orcid":false,"given":"Lei","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9506-6903","authenticated-orcid":false,"given":"Jingju","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahai","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"issue":"7587","key":"39_CR1","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"39_CR2","unstructured":"Berner, C., et al.: Dota 2 with large scale deep reinforcement learning. arXiv Preprint. arXiv:1912.06680 (2019)"},{"issue":"7782","key":"39_CR3","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","journal-title":"Nature"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Greenwald, L., Shanley, R.: Automated planning for remote penetration testing. In: MILCOM 2009\u20132009 IEEE Military Communications Conference, pp. 1\u20137 (2009)","DOI":"10.1109\/MILCOM.2009.5379852"},{"key":"39_CR5","unstructured":"Babaeizadeh, M., et al.: Reinforcement learning through asynchronous advantage actor-critic on a GPU. arXiv Preprint. arXiv:1611.06256 (2016)"},{"key":"39_CR6","first-page":"279","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8, 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Van Seijen, H., et al.: A theoretical and empirical analysis of expected SARSA. In: 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, pp. 177\u2013184 (2009)","DOI":"10.1109\/ADPRL.2009.4927542"},{"issue":"19","key":"39_CR8","doi-asserted-by":"publisher","first-page":"8823","DOI":"10.3390\/app11198823","volume":"11","author":"S Zhou","year":"2021","unstructured":"Zhou, S., et al.: Autonomous penetration testing based on improved deep q-network. Appl. Sci. 11(19), 8823 (2021)","journal-title":"Appl. Sci."},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Chowdhary, A., et al.: Autonomous security analysis and penetration testing. In: 2020 16th International Conference on Mobility, Sensing and Networking (MSN), pp. 508\u2013515 (2020)","DOI":"10.1109\/MSN50589.2020.00086"},{"key":"39_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124117","volume":"252","author":"M Geng","year":"2024","unstructured":"Geng, M., et al.: HiSOMA: a hierarchical multi-agent model integrating self-organizing neural networks with multi-agent deep reinforcement learning. Expert Syst. Appl. 252, 124117 (2024)","journal-title":"Expert Syst. Appl."},{"issue":"11","key":"39_CR11","doi-asserted-by":"publisher","first-page":"10901","DOI":"10.1109\/TII.2023.3240758","volume":"19","author":"X Wang","year":"2023","unstructured":"Wang, X., et al.: Hierarchical free gait motion planning for hexapod robots using deep reinforcement learning. IEEE Trans. Industr. Inf. 19(11), 10901\u201310912 (2023)","journal-title":"IEEE Trans. Industr. Inf."},{"issue":"4","key":"39_CR12","doi-asserted-by":"publisher","first-page":"3131","DOI":"10.1109\/TWC.2023.3305567","volume":"23","author":"X Li","year":"2023","unstructured":"Li, X., et al.: Intelligent spectrum sensing and access with partial observation based on hierarchical multi-agent deep reinforcement learning. IEEE Trans. Wireless Commun. 23(4), 3131\u20133145 (2023)","journal-title":"IEEE Trans. Wireless Commun."},{"key":"39_CR13","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"39_CR14","unstructured":"Inoue, Y., Ohashi, H.: Prompter: utilizing large language model prompting for a data efficient embodied instruction following. arXiv Preprint. arXiv:2211.03267 (2022)"},{"key":"39_CR15","unstructured":"Ahn, M., et al.: Do as I can, not as I say: grounding language in robotic affordances. arXiv Preprint. arXiv:2204.01691 (2022)"},{"key":"39_CR16","doi-asserted-by":"crossref","unstructured":"Yao, S., et al.: Keep calm and explore: language models for action generation in text-based games. arXiv Preprint. arXiv:2010.02903 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.704"},{"key":"39_CR17","unstructured":"Hu, H., Sadigh, D.: Language instructed reinforcement learning for human-AI coordination. In: International Conference on Machine Learning, pp. 13584\u201313598. PMLR (2023)"},{"key":"39_CR18","unstructured":"Microsoft Defender for Research Team: CyberBattleSim (2021). https:\/\/github.com\/microsoft\/cyberbattlesim"},{"key":"39_CR19","unstructured":"Baillie, C., et al.: CyBORG: an autonomous cyber operations research gym. arXiv Preprint. arXiv:2002.10667 (2020)"},{"key":"39_CR20","doi-asserted-by":"crossref","unstructured":"Zhou, S., et al.: APRIL: towards scalable and transferable autonomous penetration testing in large action space via action embedding. IEEE Trans. Depend. Secure Comput. (2024)","DOI":"10.1109\/TDSC.2024.3518500"},{"key":"39_CR21","unstructured":"Tran, K., et al.: Deep hierarchical reinforcement agents for automated penetration testing. arXiv Preprint. arXiv:2109.06449 (2021)"}],"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\/978-981-96-9908-7_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T22:04:23Z","timestamp":1757282663000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9908-7_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819699070","9789819699087"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9908-7_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"25 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Ningbo","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}