{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T22:52:59Z","timestamp":1777589579549,"version":"3.51.4"},"reference-count":10,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"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":[[2022,4,25]]},"DOI":"10.1109\/noms54207.2022.9789835","type":"proceedings-article","created":{"date-parts":[[2022,6,9]],"date-time":"2022-06-09T17:21:22Z","timestamp":1654795282000},"page":"1-4","source":"Crossref","is-referenced-by-count":11,"title":["Cyber threat response using reinforcement learning in graph-based attack simulations"],"prefix":"10.1109","author":[{"given":"Jakob","family":"Nyberg","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology,Stockholm,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pontus","family":"Johnson","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Stockholm,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andras","family":"Mehes","sequence":"additional","affiliation":[{"name":"Ericsson,Stockholm,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref4","article-title":"Modeling Penetration Testing with Reinforcement Learning Using Capture-the-Flag Challenges: Trade-offs between Model-free Learning and A Priori Knowledge","author":"zennaro","year":"0"},{"key":"ref3","first-page":"6:1","article-title":"Adaptive Cyber Defense Against Multi-Stage Attacks Using Learning-Based POMDP","volume":"24","author":"hu","year":"2020","journal-title":"ACM Transactions on Privacy and Security"},{"key":"ref10","article-title":"Tune: A research platform for distributed model selection and training","author":"liaw","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3230833.3232799"},{"key":"ref5","article-title":"Using Cyber Terrain in Reinforcement Learning for Penetration Testing","author":"gangupantulu","year":"0"},{"key":"ref8","article-title":"Proximal Policy Optimization Algorithms","author":"schulman","year":"0","journal-title":"Tech Rep aDS Bibcode 2017arXiv170706347S Type article"},{"key":"ref7","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3100706"},{"key":"ref9","article-title":"Playing Atari with Deep Reinforcement Learning","author":"mnih","year":"0"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/CNSM52442.2021.9615542"}],"event":{"name":"NOMS 2022-2022 IEEE\/IFIP Network Operations and Management Symposium","location":"Budapest, Hungary","start":{"date-parts":[[2022,4,25]]},"end":{"date-parts":[[2022,4,29]]}},"container-title":["NOMS 2022-2022 IEEE\/IFIP Network Operations and Management Symposium"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9789703\/9789704\/09789835.pdf?arnumber=9789835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,4]],"date-time":"2022-07-04T16:10:29Z","timestamp":1656951029000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9789835\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,25]]},"references-count":10,"URL":"https:\/\/doi.org\/10.1109\/noms54207.2022.9789835","relation":{},"subject":[],"published":{"date-parts":[[2022,4,25]]}}}