{"id":"https://openalex.org/W4414756992","doi":"https://doi.org/10.23919/cnsm67658.2025.11297482","title":"Learning Optimal Defender Strategies for CAGE-2 using a POMDP Model","display_name":"Learning Optimal Defender Strategies for CAGE-2 using a POMDP Model","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W4414756992","doi":"https://doi.org/10.23919/cnsm67658.2025.11297482"},"language":"en","primary_location":{"id":"doi:10.23919/cnsm67658.2025.11297482","is_oa":false,"landing_page_url":"https://doi.org/10.23919/cnsm67658.2025.11297482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 21st International Conference on Network and Service Management (CNSM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.06539","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112460754","display_name":"Duc Huy Le","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Duc Huy Le","raw_affiliation_strings":["KTH Royal Institute of Technology,Dept. of Computer Science,Stockholm,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Dept. of Computer Science,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035040105","display_name":"Rolf Stadler","orcid":"https://orcid.org/0000-0001-6039-8493"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Rolf Stadler","raw_affiliation_strings":["KTH Royal Institute of Technology,Dept. of Computer Science,Stockholm,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Dept. of Computer Science,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31143106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14257","display_name":"Advanced Measurement and Detection Methods","score":0.7799999713897705,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14257","display_name":"Advanced Measurement and Detection Methods","score":0.7799999713897705,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.8361999988555908},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5931000113487244},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5817999839782715},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5489000082015991},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5231000185012817},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5069000124931335},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.47540000081062317},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4603999853134155}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.8361999988555908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6998000144958496},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5931000113487244},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5817999839782715},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5489000082015991},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5231000185012817},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5069000124931335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5011000037193298},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.47540000081062317},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4603999853134155},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42730000615119934},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.426800012588501},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.30329999327659607},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C2984634286","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision process","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.25949999690055847},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.23919/cnsm67658.2025.11297482","is_oa":false,"landing_page_url":"https://doi.org/10.23919/cnsm67658.2025.11297482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 21st International Conference on Network and Service Management (CNSM)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.06539","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.06539","pdf_url":"https://arxiv.org/pdf/2509.06539","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.06539","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.06539","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.06539","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.06539","pdf_url":"https://arxiv.org/pdf/2509.06539","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"CAGE-2":[0,32,48,70,106,114,131],"is":[1,84],"an":[2,22,65],"accepted":[3],"benchmark":[4],"for":[5,31,47,69],"learning":[6],"and":[7,71,88,117,145],"evaluating":[8],"defender":[9,19,29,67,143],"strategies":[10],"against":[11,25],"cyberattacks.":[12],"It":[13],"reflects":[14],"a":[15,18,44,73],"scenario":[16],"where":[17],"agent":[20],"protects":[21],"IT":[23],"infrastructure":[24],"various":[26],"attacks.":[27],"Many":[28],"methods":[30],"have":[33],"been":[34],"proposed":[35],"in":[36,112],"the":[37,50,95,100,105,113,125,130,141,146],"literature.":[38],"In":[39],"this":[40,61,78],"paper,":[41],"we":[42,63],"construct":[43],"formal":[45],"model":[46],"using":[49],"framework":[51],"of":[52,104,123],"Partially":[53],"Observable":[54],"Markov":[55],"Decision":[56],"Process":[57],"(POMDP).":[58],"Based":[59],"on":[60,86,129],"model,":[62],"define":[64],"optimal":[66],"strategy":[68,144],"introduce":[72],"method":[74,111,128,137],"to":[75,93,99],"efficiently":[76],"learn":[77],"strategy.":[79],"Our":[80],"method,":[81],"called":[82],"BF-PPO,":[83],"based":[85],"PPO,":[87],"it":[89],"uses":[90],"particle":[91],"filter":[92],"mitigate":[94],"computational":[96],"complexity":[97],"due":[98],"large":[101],"state":[102],"space":[103],"model.":[107],"We":[108,133],"evaluate":[109],"our":[110,136],"CybORG":[115],"environment":[116],"compare":[118],"its":[119],"performance":[120],"with":[121],"that":[122,135],"CARDIFF,":[124],"highest":[126],"ranked":[127],"leaderboard.":[132],"find":[134],"outperforms":[138],"CARDIFF":[139],"regarding":[140],"learned":[142],"required":[147],"training":[148],"time.":[149]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-02T00:00:00"}