{"id":"https://openalex.org/W4404130317","doi":"https://doi.org/10.1145/3689933.3690835","title":"Entity-based Reinforcement Learning for Autonomous Cyber Defence","display_name":"Entity-based Reinforcement Learning for Autonomous Cyber Defence","publication_year":2023,"publication_date":"2023-11-06","ids":{"openalex":"https://openalex.org/W4404130317","doi":"https://doi.org/10.1145/3689933.3690835"},"language":"en","primary_location":{"id":"doi:10.1145/3689933.3690835","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3689933.3690835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Autonomous Cybersecurity","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.17647","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014637397","display_name":"Isaac Thompson","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Isaac Symes Thompson","raw_affiliation_strings":["The Alan Turing Institute, London, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0009-7908-4107","affiliations":[{"raw_affiliation_string":"The Alan Turing Institute, London, United Kingdom","institution_ids":["https://openalex.org/I4210128584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080813974","display_name":"Alberto Caron","orcid":"https://orcid.org/0000-0001-5643-2302"},"institutions":[{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alberto Caron","raw_affiliation_strings":["The Alan Turing Institute, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-5643-2302","affiliations":[{"raw_affiliation_string":"The Alan Turing Institute, London, United Kingdom","institution_ids":["https://openalex.org/I4210128584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080048241","display_name":"Chris Hicks","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chris Hicks","raw_affiliation_strings":["The Alan Turing Institute, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-6340-004X","affiliations":[{"raw_affiliation_string":"The Alan Turing Institute, London, United Kingdom","institution_ids":["https://openalex.org/I4210128584"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008006072","display_name":"Vasilios Mavroudis","orcid":"https://orcid.org/0000-0003-2667-5906"},"institutions":[{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vasilios Mavroudis","raw_affiliation_strings":["The Alan Turing Institute, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-2667-5906","affiliations":[{"raw_affiliation_string":"The Alan Turing Institute, London, United Kingdom","institution_ids":["https://openalex.org/I4210128584"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210128584"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"56","last_page":"67"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10917","display_name":"Smart Grid Security and Resilience","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7776534557342529},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6359588503837585},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4529340863227844},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3944382965564728},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3434441089630127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33047038316726685},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.216970294713974}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7776534557342529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6359588503837585},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4529340863227844},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3944382965564728},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3434441089630127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33047038316726685},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.216970294713974},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3689933.3690835","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3689933.3690835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Autonomous Cybersecurity","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.17647","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.17647","pdf_url":"https://arxiv.org/pdf/2410.17647","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.17647","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.17647","pdf_url":"https://arxiv.org/pdf/2410.17647","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320312768","display_name":"GCHQ","ror":"https://ror.org/052mq0r90"},{"id":"https://openalex.org/F4320313467","display_name":"Alan Turing Institute","ror":"https://ror.org/035dkdb55"},{"id":"https://openalex.org/F4320332972","display_name":"Defence Science and Technology Laboratory","ror":"https://ror.org/04jswqb94"},{"id":"https://openalex.org/F4320335334","display_name":"Defence Science and Technology Group","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404130317.pdf","grobid_xml":"https://content.openalex.org/works/W4404130317.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2101355568","https://openalex.org/W2132022337","https://openalex.org/W2170400507","https://openalex.org/W2559655401","https://openalex.org/W2560674852","https://openalex.org/W2612690371","https://openalex.org/W2747329762","https://openalex.org/W2952298682","https://openalex.org/W3020831056","https://openalex.org/W3107852229","https://openalex.org/W3209929740","https://openalex.org/W3212488318","https://openalex.org/W3213774989","https://openalex.org/W3216772467","https://openalex.org/W4281656599","https://openalex.org/W4307964230"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"A":[0],"significant":[1],"challenge":[2],"for":[3,25,191,210],"autonomous":[4,70,116,219],"cyber":[5,71,220],"defence":[6,118,221],"is":[7,23],"ensuring":[8],"a":[9,135,155,197],"defensive":[10],"agent's":[11],"ability":[12,190],"to":[13,27,50,77,82,194,200,214],"generalise":[14,81],"across":[15,170],"diverse":[16],"network":[17,40,85,117,172,233],"topologies":[18,86],"and":[19,46,66,104,126,165,187],"configurations.":[20],"This":[21,140],"capability":[22],"necessary":[24],"agents":[26,79],"remain":[28],"effective":[29],"when":[30],"deployed":[31],"in":[32,149,203,231],"dynamically":[33],"changing":[34],"environments,":[35],"such":[36],"as":[37,92],"an":[38,130,181],"enterprise":[39],"where":[41,54,123],"devices":[42],"may":[43],"frequently":[44],"join":[45],"leave.":[47],"Standard":[48],"approaches":[49],"deep":[51],"reinforcement":[52,121,212],"learning,":[53,122],"policies":[55,226],"are":[56,132],"parameterised":[57],"using":[58,119],"fixed-input":[59],"multi-layer":[60],"perceptrons":[61],"(MLP)":[62],"expect":[63],"fixed-size":[64],"observation":[65,103,125],"action":[67,105,127],"spaces.":[68,106],"In":[69],"defence,":[72],"this":[73,109,177],"makes":[74],"it":[75],"hard":[76],"develop":[78],"that":[80,176],"environments":[83],"with":[84],"different":[87,198],"from":[88],"those":[89,201],"trained":[90],"on,":[91],"the":[93,98,102,113,124,143,159,189,208,216],"number":[94],"of":[95,101,115,129,137,145,196,218,228],"nodes":[96],"affects":[97],"natural":[99],"size":[100,199],"To":[107],"overcome":[108],"limitation,":[110],"we":[111,153],"reframe":[112],"problem":[114],"entity-based":[120,211],"space":[128],"agent":[131],"decomposed":[133],"into":[134],"collection":[136],"discrete":[138],"entities.":[139],"framework":[141],"enables":[142],"use":[144],"policy":[146,157,183],"parameterisations":[147],"specialised":[148],"compositional":[150],"generalisation.":[151],"Namely,":[152],"train":[154],"Transformer-based":[156],"on":[158,184],"Yawning":[160],"Titan":[161],"cyber-security":[162],"simulation":[163],"environment":[164],"test":[166],"its":[167],"generalisation":[168,193],"capabilities":[169],"various":[171],"topologies.":[173],"We":[174],"demonstrate":[175],"approach":[178],"significantly":[179],"outperforms":[180],"MLP-based":[182],"fixed":[185],"networks,":[186],"has":[188],"zero-shot":[192],"networks":[195],"seen":[202],"training.":[204],"These":[205],"findings":[206],"highlight":[207],"potential":[209],"learning":[213],"advance":[215],"field":[217],"by":[222],"providing":[223],"more":[224],"generalisable":[225],"capable":[227],"handling":[229],"variations":[230],"real-world":[232],"environments.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
