{"id":"https://openalex.org/W7058013932","doi":null,"title":"LLM-Directed Agent Models in Cyberspace","display_name":"LLM-Directed Agent Models in Cyberspace","publication_year":2024,"publication_date":"2024-05-01","ids":{"openalex":"https://openalex.org/W7058013932"},"language":"en","primary_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/156291","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/156291","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/156291/1/laney-splaney-sm-eecs-2024-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dspace.mit.edu/bitstream/1721.1/156291/1/laney-splaney-sm-eecs-2024-thesis.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Laney, Samuel P.","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Laney, Samuel P.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.41920000314712524,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.41920000314712524,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10734","display_name":"Information and Cyber Security","score":0.17829999327659607,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.13050000369548798,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9919999837875366},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.6990000009536743},{"id":"https://openalex.org/keywords/network-penetration-testing","display_name":"network penetration testing","score":0.8529999852180481},{"id":"https://openalex.org/keywords/capture-the-flag-challenges","display_name":"capture-the-flag challenges","score":0.7860000133514404},{"id":"https://openalex.org/keywords/automated-vulnerability-assessment","display_name":"automated vulnerability assessment","score":0.5440000295639038},{"id":"https://openalex.org/keywords/hierarchical-agent-architecture","display_name":"hierarchical agent architecture","score":0.7940000295639038},{"id":"https://openalex.org/keywords/cybersecurity-automation","display_name":"cybersecurity automation","score":0.5550000071525574},{"id":"https://openalex.org/keywords/assessment-framework","display_name":"evaluation framework","score":0.4690000116825104}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6952999830245972},{"id":"https://openalex.org/C2781241145","wikidata":"https://www.wikidata.org/wiki/Q204606","display_name":"Cyberspace","level":3,"score":0.6589000225067139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5634999871253967},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.516700029373169},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.49410000443458557},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4862000048160553},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.4108000099658966},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.34209999442100525},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3393999934196472},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.30079999566078186},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C137703981","wikidata":"https://www.wikidata.org/wiki/Q4692093","display_name":"Agent architecture","level":3,"score":0.2948000133037567},{"id":"https://openalex.org/C5894958","wikidata":"https://www.wikidata.org/wiki/Q2297769","display_name":"Software agent","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:dspace.mit.edu:1721.1/156291","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/156291","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/156291/1/laney-splaney-sm-eecs-2024-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/156291","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/156291","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/156291/1/laney-splaney-sm-eecs-2024-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7058013932.pdf","grobid_xml":"https://content.openalex.org/works/W7058013932.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W2626778328","https://openalex.org/W2896457183","https://openalex.org/W2952769376","https://openalex.org/W3030163527","https://openalex.org/W3083410900","https://openalex.org/W3118781290","https://openalex.org/W3177813494","https://openalex.org/W4221152848","https://openalex.org/W4226278401","https://openalex.org/W4236521339","https://openalex.org/W4319165647","https://openalex.org/W4320351164","https://openalex.org/W4327810158","https://openalex.org/W4360836968","https://openalex.org/W4383473935","https://openalex.org/W4384918448","https://openalex.org/W4385682136","https://openalex.org/W4385848840","https://openalex.org/W4386081444","https://openalex.org/W4387595846","https://openalex.org/W4388926373","https://openalex.org/W4390041933","https://openalex.org/W4390690464","https://openalex.org/W4390723197","https://openalex.org/W4390874280","https://openalex.org/W4391876619","https://openalex.org/W4391941782","https://openalex.org/W4391987669","https://openalex.org/W4392490408","https://openalex.org/W4393027028","https://openalex.org/W4396219010","https://openalex.org/W4399528455","https://openalex.org/W4402671800","https://openalex.org/W4402716477","https://openalex.org/W4406214400","https://openalex.org/W7133209886","https://openalex.org/W7133231369","https://openalex.org/W7133240538"],"related_works":["https://openalex.org/W4409156842","https://openalex.org/W4416251023","https://openalex.org/W6948053009","https://openalex.org/W4415883730","https://openalex.org/W7115599674","https://openalex.org/W6968780041","https://openalex.org/W4391987669","https://openalex.org/W4413176392","https://openalex.org/W6891867882","https://openalex.org/W7212039816"],"abstract_inverted_index":{"Network":[0],"penetration":[1,51,185],"testing,":[2],"a":[3,115,122,134,173],"proactive":[4],"method":[5],"for":[6,31,49,78,101,166],"identifying":[7],"vulnerabilities":[8],"in":[9,23,70,84,103,118,145,163,181,198,214,230,236],"cy-":[10],"berspace,":[11],"has":[12],"long":[13],"been":[14],"the":[15,42,56,61,80,94,129,146,158,212],"domain":[16],"of":[17,34,44,82,124,136,148,193,211],"human":[18,68],"experts.":[19],"However,":[20],"rapid":[21],"advancements":[22],"machine":[24],"learning":[25],"have":[26],"opened":[27],"up":[28],"new":[29],"possibilities":[30],"automating":[32,50],"many":[33],"these":[35,237],"tasks.":[36,168],"This":[37,72,191],"thesis":[38,108],"aims":[39,153],"to":[40,128,154,176,217,233],"explore":[41],"application":[43],"Large":[45],"Language":[46],"Models":[47],"(LLMs)":[48],"tests":[52],"and":[53,66,97,141,161],"Cyber":[54],"Capture":[55],"Flag":[57],"(CTF)":[58],"challenges,":[59,88,150],"bridging":[60],"gap":[62],"between":[63],"static":[64],"tools":[65],"dynamic":[67],"intuition":[69],"cybersecurity.":[71],"work":[73,152,171,232],"provides":[74],"an":[75,90,110,178],"evaluation":[76],"framework":[77],"assessing":[79],"performance":[81,235],"LLMs":[83,102,165,203],"autonomously":[85],"solving":[86],"CTF":[87,149],"with":[89,188],"emphasis":[91],"on":[92,121],"understanding":[93],"capabilities,":[95,206],"limitations,":[96],"best":[98,159],"prompting":[99],"strategies":[100],"this":[104,107,151,170,231],"domain.":[105],"Notably,":[106],"presents":[109],"agent":[111,137,180],"configuration":[112],"that":[113],"offers":[114],"102%":[116],"improvement":[117],"challenge":[119],"completion":[120],"database":[123],"PicoCTF":[125],"challenges":[126],"compared":[127],"published":[130],"baseline.":[131],"By":[132],"analyzing":[133],"variety":[135],"strategies,":[138],"response":[139],"formats,":[140],"historical":[142],"action":[143],"representations":[144],"context":[147],"provide":[155],"insights":[156],"into":[157],"practices":[160],"limitations":[162],"leveraging":[164],"cybersecurity":[167],"Additionally,":[169],"proposes":[172],"hierarchical":[174],"architecture":[175],"guide":[177],"LLM-enabled":[179],"performing":[182],"complex,":[183,219],"multi-step":[184,220],"testing":[186],"tasks":[187,221],"strategic":[189],"foresight.":[190],"proof":[192],"concept":[194],"approach":[195],"shows":[196],"success":[197],"entry":[199],"level":[200],"challenges.":[201],"While":[202],"exhibit":[204],"impressive":[205],"they":[207],"are":[208],"limited":[209],"out":[210],"box":[213],"their":[215],"ability":[216],"solve":[218],"requiring":[222],"exploration,":[223],"necessitating":[224],"approaches":[225],"such":[226],"as":[227],"those":[228],"described":[229],"improve":[234],"areas.":[238]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}