{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T08:02:30Z","timestamp":1764835350511,"version":"3.46.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T00:00:00Z","timestamp":1756166400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T00:00:00Z","timestamp":1756166400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,26]]},"DOI":"10.1109\/pst65910.2025.11268866","type":"proceedings-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:40:04Z","timestamp":1764787204000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Cyber Threat Mitigation with Knowledge-Infused Reinforcement Learning and LLM-Guided Policies"],"prefix":"10.1109","author":[{"given":"Md. Shamim","family":"Towhid","sequence":"first","affiliation":[{"name":"National Research Council,Canada"}]},{"given":"Shahrear","family":"Iqbal","sequence":"additional","affiliation":[{"name":"National Research Council,Canada"}]},{"given":"Euclides Carlos Pinto","family":"Neto","sequence":"additional","affiliation":[{"name":"National Research Council,Canada"}]},{"given":"Nashid","family":"Shahriar","sequence":"additional","affiliation":[{"name":"University of Regina,Department of Computer Science"}]},{"given":"Scott","family":"Buffett","sequence":"additional","affiliation":[{"name":"National Research Council,Canada"}]},{"given":"Madeena","family":"Sultana","sequence":"additional","affiliation":[{"name":"Defence Research and Development,Canada"}]},{"given":"Adrian","family":"Taylor","sequence":"additional","affiliation":[{"name":"Defence Research and Development,Canada"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"100306","DOI":"10.1016\/j.array.2023.100306","article-title":"Ensuring network security with a robust intrusion detection system using ensemble-based machine learning","volume":"19","author":"Hossain","year":"2023","journal-title":"Array"},{"volume-title":"MITRE ATT&CK","year":"2025","key":"ref2"},{"issue":"05","key":"ref3","doi-asserted-by":"crossref","first-page":"15","DOI":"10.3991\/ijoe.v20i05.48229","article-title":"Deep reinforcement learning approach for cyberattack detection","volume":"20","author":"Tareq","year":"2024","journal-title":"International Journal of Online and Biomedical Engineering (iJOE)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685361"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"102002","DOI":"10.1016\/j.inffus.2023.102002","article-title":"Fed-inforce-fusion: A federated reinforcement-based fusion model for security and privacy protection of iomt networks against cyber-attacks","volume":"101","author":"Khan","year":"2024","journal-title":"Information Fusion"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICC42927.2021.9500698"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"112963","DOI":"10.1016\/j.eswa.2019.112963","article-title":"Application of deep reinforcement learning to intrusion detection for supervised problems","volume":"141","author":"Lopez-Martin","year":"2020","journal-title":"Expert Systems with Applications"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CyberSA.2018.8551383"},{"article-title":"The unified kill chain","year":"2021","author":"Pols","key":"ref9"},{"article-title":"Reinforcement learning for autonomous resilient cyber defenc e","volume-title":"Black Hat USA","author":"Miles","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s00607-024-01344-4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3305218.3305239"},{"key":"ref13","article-title":"Evaluation of reinforcement learning for autonomous penetration testing using a3c, q-learning and dqn","author":"Becker","year":"2024","journal-title":"arXiv preprint arXiv:2407.15656"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1812\/1\/012039"},{"article-title":"Causality-driven hierarchical structure discovery for reinforcement learning","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems, ser. NIPS \u201822.","author":"Peng","key":"ref15"},{"key":"ref16","article-title":"Causally correct partial models for reinforcement learning","author":"Rezende","year":"2020","journal-title":"arXiv preprint arXiv:2002.02836"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3121050.3121062"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/524"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2023.3299435"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3497992"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICMCIS61231.2024.10540988"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5220\/0006639801080116"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5220\/0006105602530262"},{"key":"ref25","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","volume-title":"arXiv preprint arXiv:2404.14219","author":"Abdin","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CSR61664.2024.10679494"},{"key":"ref27","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv:1707.06347"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CNS59707.2023.10288677"},{"key":"ref29","article-title":"Cyborg: An autonomous cyber operations research gym","author":"Baillie","year":"2020","journal-title":"arXiv preprint arXiv:2002.10667"}],"event":{"name":"2025 22nd Annual International Conference on Privacy, Security, and Trust (PST)","start":{"date-parts":[[2025,8,26]]},"location":"Fredericton, NB, Canada","end":{"date-parts":[[2025,8,28]]}},"container-title":["2025 22nd Annual International Conference on Privacy, Security, and Trust (PST)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11268482\/11268814\/11268866.pdf?arnumber=11268866","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T07:58:45Z","timestamp":1764835125000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11268866\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,26]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/pst65910.2025.11268866","relation":{},"subject":[],"published":{"date-parts":[[2025,8,26]]}}}