{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T16:29:10Z","timestamp":1771518550877,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"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":[[2024,9,2]]},"DOI":"10.1109\/csr61664.2024.10679510","type":"proceedings-article","created":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T17:21:51Z","timestamp":1727198511000},"page":"262-269","source":"Crossref","is-referenced-by-count":8,"title":["Leveraging Reinforcement Learning in Red Teaming for Advanced Ransomware Attack Simulations"],"prefix":"10.1109","author":[{"given":"Cheng","family":"Wang","sequence":"first","affiliation":[{"name":"Deloitte & Touche LLP"}]},{"given":"Christopher","family":"Redino","sequence":"additional","affiliation":[{"name":"Deloitte & Touche LLP"}]},{"given":"Ryan","family":"Clark","sequence":"additional","affiliation":[{"name":"Deloitte & Touche LLP"}]},{"given":"Abdul","family":"Rahman","sequence":"additional","affiliation":[{"name":"Deloitte & Touche LLP"}]},{"given":"Sal","family":"Aguinaga","sequence":"additional","affiliation":[{"name":"Deloitte & Touche LLP"}]},{"given":"Sathvik","family":"Murli","sequence":"additional","affiliation":[{"name":"Deloitte & Touche LLP"}]},{"given":"Dhruv","family":"Nandakumar","sequence":"additional","affiliation":[{"name":"Deloitte & Touche LLP"}]},{"given":"Roland","family":"Rao","sequence":"additional","affiliation":[{"name":"Deloitte & Touche LLP"}]},{"given":"Lanxiao","family":"Huang","sequence":"additional","affiliation":[{"name":"Virginia Tech"}]},{"given":"Daniel","family":"Radke","sequence":"additional","affiliation":[{"name":"Deloitte & Touche LLP"}]},{"given":"Edward","family":"Bowen","sequence":"additional","affiliation":[{"name":"Deloitte & Touche LLP"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3268535"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.12.001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2017.0-119"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S1361-3723(18)30097-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IAW.2004.1437806"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3514229"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3229710.3229726"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88418-5_12"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/PST52912.2021.9647816"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.icte.2020.11.001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISGTLatinAmerica52371.2021.9543031"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3112056"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.09.025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10796-020-10017-4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11416-015-0261-z"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/EWDTS50664.2020.9225141"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI50451.2021.9659947"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/DSC54232.2022.9888919"},{"key":"ref19","author":"Rishu","year":"2023","journal-title":"Enhancing exfiltration path analysis using reinforcement learning"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA55696.2022.00282"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SoutheastCon51012.2023.10115173"},{"key":"ref22","volume-title":"On cyber: towards an operational art for cyber conflict","author":"Conti","year":"2018"},{"key":"ref23","article-title":"Using cyber terrain in reinforcement learning for penetration testing","author":"Gangupantulu","year":"2021","journal-title":"Submitted ACM ASIACCS 2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref25","article-title":"Policy gradi-ent methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref26","author":"Schulman","year":"2017","journal-title":"Prox-imal policy optimization algorithms"},{"key":"ref27","author":"Schulman","year":"2015","journal-title":"High-dimensional continuous control using generalized advantage estimation"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/EEE.2005.86"}],"event":{"name":"2024 IEEE International Conference on Cyber Security and Resilience (CSR)","location":"London, United Kingdom","start":{"date-parts":[[2024,9,2]]},"end":{"date-parts":[[2024,9,4]]}},"container-title":["2024 IEEE International Conference on Cyber Security and Resilience (CSR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10679369\/10679342\/10679510.pdf?arnumber=10679510","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T05:22:36Z","timestamp":1727241756000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10679510\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,2]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/csr61664.2024.10679510","relation":{},"subject":[],"published":{"date-parts":[[2024,9,2]]}}}