{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T18:53:58Z","timestamp":1787165638941,"version":"build-2736575974"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T00:00:00Z","timestamp":1635120000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T00:00:00Z","timestamp":1635120000000},"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":[[2021,10,25]]},"DOI":"10.23919\/cnsm52442.2021.9615542","type":"proceedings-article","created":{"date-parts":[[2021,12,2]],"date-time":"2021-12-02T15:30:34Z","timestamp":1638459034000},"page":"509-517","source":"Crossref","is-referenced-by-count":18,"title":["Learning Intrusion Prevention Policies through Optimal Stopping"],"prefix":"10.23919","author":[{"given":"Kim","family":"Hammar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rolf","family":"Stadler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"0","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref32","author":"peskir","year":"2006","journal-title":"Optimal stopping and free-boundary problems"},{"key":"ref31","author":"shirayev","year":"2007","journal-title":"Optimal Stopping Rules"},{"key":"ref30","author":"wald","year":"1947","journal-title":"Sequential Analysis"},{"key":"ref37","author":"hammar","year":"2021","journal-title":"gym-optimal-intrusion-response"},{"key":"ref36","first-page":"2","article-title":"Docker: lightweight linux containers for consistent development and deployment","volume":"2014","author":"merkel","year":"2014","journal-title":"Linux Journal"},{"key":"ref35","author":"hammar","year":"2021","journal-title":"Learning intrusion prevention policies through optimal stopping"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Int Conf Learning Representations 2014"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/CNSM50824.2020.9269092"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5220\/0006197105590566"},{"key":"ref12","volume":"i","author":"bertsekas","year":"2005","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781316471104"},{"key":"ref14","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref15","article-title":"Deep reinforcement learning for cyber security","volume":"abs 1906 5799","author":"nguyen","year":"2019","journal-title":"CoRR"},{"key":"ref16","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1214\/08-AAP566"},{"key":"ref18","article-title":"Online reinforcement learning of optimal threshold policies for markov decision processes","volume":"abs 1912 10325","author":"roy","year":"2019","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2878570"},{"key":"ref28","author":"watkins","year":"1989","journal-title":"Learning from delayed rewards"},{"key":"ref4","author":"alpcan","year":"2010","journal-title":"Network Security A Decision and Game-Theoretic Approach"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1287\/opre.26.2.282"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.23919\/TMA.2018.8506545"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.stamet.2005.05.003"},{"key":"ref29","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref5","first-page":"439","article-title":"Adversarial attacks on continuous authentication security: A dynamic game approach","author":"santa?","year":"2019","journal-title":"Decision and Game Theory for Security"},{"key":"ref8","first-page":"99","article-title":"A supervisory control approach to dynamic cyber-security","author":"rasouli","year":"2014","journal-title":"Decision and Game Theory for Security"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/srep42308"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3230833.3232799"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2819967"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.istr.2005.08.001"},{"key":"ref20","article-title":"Modeling penetration testing with reinforcement learning using capture-the-flag challenges and tabular q-learning","volume":"abs 2005 12632","author":"zennaro","year":"2020","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1609\/icaps.v30i1.6666","article-title":"Pomdp + information-decay: Incorporating defender's behaviour in autonomous penetration testing","volume":"30","author":"schwartz","year":"0","journal-title":"Proceedings of the International Conference on Automated Planning and Scheduling"},{"key":"ref24","author":"howard","year":"1960","journal-title":"Dynamic Programming and Markov Processes"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref26","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"ref25","author":"kaelbling","year":"1996","journal-title":"Planning and acting in partially observable stochastic domains"}],"event":{"name":"2021 17th International Conference on Network and Service Management (CNSM)","location":"Izmir, Turkey","start":{"date-parts":[[2021,10,25]]},"end":{"date-parts":[[2021,10,29]]}},"container-title":["2021 17th International Conference on Network and Service Management (CNSM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9615441\/9615442\/09615542.pdf?arnumber=9615542","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T19:03:10Z","timestamp":1673895790000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9615542\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,25]]},"references-count":37,"URL":"https:\/\/doi.org\/10.23919\/cnsm52442.2021.9615542","relation":{},"subject":[],"published":{"date-parts":[[2021,10,25]]}}}