{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T06:14:16Z","timestamp":1783577656392,"version":"3.55.0"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"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":[[2026,6,22]]},"DOI":"10.1109\/dsn69566.2026.00079","type":"proceedings-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:41:43Z","timestamp":1783539703000},"page":"813-824","source":"Crossref","is-referenced-by-count":0,"title":["Generalizable Graph-based Reinforcement Learning Agents for Automated Cyber Defense"],"prefix":"10.1109","author":[{"given":"Isaiah J.","family":"King","sequence":"first","affiliation":[{"name":"Cybermonic LLC,McLean,VA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Bowman","sequence":"additional","affiliation":[{"name":"Cybermonic LLC,McLean,VA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"H. Howie","family":"Huang","sequence":"additional","affiliation":[{"name":"Cybermonic LLC,McLean,VA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Automated cyber defence: A review","author":"Vyas","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/DSC50466.2020.00065"},{"key":"ref3","first-page":"15","article-title":"Sdn-based moving target defense using multi-agent reinforcement learning","volume-title":"Proceedings of the first International Conference on Autonomous Intelligent Cyber defense Agents (AICA 2021)","author":"Chowdhary"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-64793-3_4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA55696.2022.00213"},{"issue":"1","key":"ref6","first-page":"7","article-title":"Machine learning for autonomous cyber defense","volume":"22","author":"Ridley","year":"2018","journal-title":"The Next Wave"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2011.5967363"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.14174"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2022.09.029"},{"key":"ref10","article-title":"Acd-g: Enhancing autonomous cyber defense agent generalization through graph embedded network representation","volume-title":"International Conference on Machine Learning","author":"Collyer"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI50451.2021.9659947"},{"key":"ref12","article-title":"A model-based, decisiontheoretic perspective on automated cyber response","author":"Booker","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3488932.3527286"},{"key":"ref14","article-title":"Incorporating deception into cyberbattlesim for autonomous defense","author":"Walter","year":"2021"},{"key":"ref15","article-title":"Beyond cage: Investigating generalization of learned autonomous network defense policies","author":"Wolk","year":"2022"},{"key":"ref16","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018"},{"key":"ref17","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"ref18","article-title":"Symbolic relational deep rein-forcement learning based on graph neural networks","author":"Janisch","year":"2020"},{"key":"ref19","volume-title":"Ttcp cage challenge 4","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref22","article-title":"Fast graph representation learning with PyTorch Geometric","volume-title":"ICLR Workshop on Representation Learning on Graphs and Manifolds","author":"Fey"},{"key":"ref23","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref24","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASONAM55673.2022.10068589"},{"key":"ref26","article-title":"TTCP CAGE challenge 2","volume-title":"AAAI-22 Workshop on Artificial Intelligence for Cyber Security (AICS)"},{"issue":"1","key":"ref27","first-page":"17","article-title":"On the evolution of random graphs","volume":"5","author":"Erd\u0151s","year":"1960","journal-title":"Publ. math. inst. hung. acad. sci"},{"key":"ref28","first-page":"49","article-title":"Dynamic network reconfiguration for entropy maximization using deep reinforcement learning","volume-title":"Learning on Graphs Conference","author":"Doorman"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098061"},{"key":"ref30","article-title":"A comparative study of deep reinforcement learning models: Dqn vs ppo vs a2c","author":"De La Fuente","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/4235.585893"},{"issue":"268","key":"ref32","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref33","article-title":"CardiffUni CAGE2 submission","author":"Hannay","year":"2022"},{"key":"ref34","article-title":"Sub-policy adaptation for hierarchical reinforcement learning","author":"Li","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i28.35158"},{"issue":"20","key":"ref36","first-page":"10","article-title":"Graph attention networks","volume":"1050","author":"Velickovic","year":"2017","journal-title":"stat"},{"key":"ref37","article-title":"How powerful are graph neural networks?","volume-title":"International Conference on Learning Representations","author":"Xu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.1.1"},{"key":"ref39","article-title":"The need for biases in learning generalizations","author":"Mitchell","year":"1980","journal-title":"Rutgers Technical Report"},{"key":"ref40","article-title":"Relational inductive bias for physical construction in humans and machines","author":"Hamrick","year":"2018"},{"key":"ref41","article-title":"Learning combinatorial optimization algorithms over graphs","volume":"30","author":"Khalil","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref42","article-title":"Nervenet: Learning structured policy with graph neural networks","volume-title":"International conference on learning representations","author":"Wang"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3290480.3290494"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3560830.3563732"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TrustCom\/BigDataSE.2018.00041"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1117\/12.2559319"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/6378218"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1812\/1\/012039"},{"key":"ref49","first-page":"423","article-title":"Evaluating ai agents for cyber defense: A comparison of deep reinforcement learning and llm approaches","volume-title":"International Conference on Intelligent Data Engineering and Automated Learning","author":"Chowdhry"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2025.3568209"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM64451.2025.11310253"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CAI64502.2025.00195"},{"key":"ref53","volume-title":"Cyber Agents for Security Testing and Learning Environments (CASTLE)","year":"2022"}],"event":{"name":"2026 56th Annual IEEE International Conference on Dependable Systems and Networks (DSN)","location":"Charlotte, NC, USA","start":{"date-parts":[[2026,6,22]]},"end":{"date-parts":[[2026,6,25]]}},"container-title":["2026 56th Annual IEEE International Conference on Dependable Systems and Networks (DSN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11593123\/11593173\/11593294.pdf?arnumber=11593294","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:23:42Z","timestamp":1783574622000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11593294\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/dsn69566.2026.00079","relation":{},"subject":[],"published":{"date-parts":[[2026,6,22]]}}}