{"id":"https://openalex.org/W4416961966","doi":"https://doi.org/10.1109/pst65910.2025.11268838","title":"RefPentester: A Knowledge-Informed Self-Reflective Penetration Testing Framework Based on Large Language Models","display_name":"RefPentester: A Knowledge-Informed Self-Reflective Penetration Testing Framework Based on Large Language Models","publication_year":2025,"publication_date":"2025-08-26","ids":{"openalex":"https://openalex.org/W4416961966","doi":"https://doi.org/10.1109/pst65910.2025.11268838"},"language":null,"primary_location":{"id":"doi:10.1109/pst65910.2025.11268838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pst65910.2025.11268838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 22nd Annual International Conference on Privacy, Security, and Trust (PST)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108936917","display_name":"Hanzheng Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I161856759","display_name":"Concordia University","ror":"https://ror.org/01qxhf360","country_code":"US","type":"education","lineage":["https://openalex.org/I161856759"]},{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA","US"],"is_corresponding":true,"raw_author_name":"Hanzheng Dai","raw_affiliation_strings":["Concordia Institute for Information Systems Engineering (CIISE), Concordia University,Montr´eal,Canada"],"affiliations":[{"raw_affiliation_string":"Concordia Institute for Information Systems Engineering (CIISE), Concordia University,Montr´eal,Canada","institution_ids":["https://openalex.org/I161856759","https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036711281","display_name":"Yuanliang Li","orcid":"https://orcid.org/0000-0002-6741-5038"},"institutions":[{"id":"https://openalex.org/I161856759","display_name":"Concordia University","ror":"https://ror.org/01qxhf360","country_code":"US","type":"education","lineage":["https://openalex.org/I161856759"]},{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Yuanliang Li","raw_affiliation_strings":["Concordia Institute for Information Systems Engineering (CIISE), Concordia University,Montr´eal,Canada"],"affiliations":[{"raw_affiliation_string":"Concordia Institute for Information Systems Engineering (CIISE), Concordia University,Montr´eal,Canada","institution_ids":["https://openalex.org/I161856759","https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101694030","display_name":"Jun Yan","orcid":"https://orcid.org/0000-0002-1520-7448"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]},{"id":"https://openalex.org/I161856759","display_name":"Concordia University","ror":"https://ror.org/01qxhf360","country_code":"US","type":"education","lineage":["https://openalex.org/I161856759"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Jun Yan","raw_affiliation_strings":["Concordia Institute for Information Systems Engineering (CIISE), Concordia University,Montr´eal,Canada"],"affiliations":[{"raw_affiliation_string":"Concordia Institute for Information Systems Engineering (CIISE), Concordia University,Montr´eal,Canada","institution_ids":["https://openalex.org/I161856759","https://openalex.org/I60158472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047051816","display_name":"Zhibo Zhang","orcid":"https://orcid.org/0000-0003-4737-4918"},"institutions":[{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhibo Zhang","raw_affiliation_strings":["Polytechnique Montr´eal,Montr´eal,Canada"],"affiliations":[{"raw_affiliation_string":"Polytechnique Montr´eal,Montr´eal,Canada","institution_ids":["https://openalex.org/I45683168"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108936917"],"corresponding_institution_ids":["https://openalex.org/I161856759","https://openalex.org/I60158472"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39537307,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.23600000143051147,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.23600000143051147,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.12380000203847885,"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/T10734","display_name":"Information and Cyber Security","score":0.11909999698400497,"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/process","display_name":"Process (computing)","score":0.5889999866485596},{"id":"https://openalex.org/keywords/hacker","display_name":"Hacker","score":0.41589999198913574},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3953999876976013},{"id":"https://openalex.org/keywords/fuzz-testing","display_name":"Fuzz testing","score":0.36230000853538513},{"id":"https://openalex.org/keywords/soundness","display_name":"Soundness","score":0.34459999203681946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.697700023651123},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5889999866485596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44209998846054077},{"id":"https://openalex.org/C86844869","wikidata":"https://www.wikidata.org/wiki/Q2798820","display_name":"Hacker","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4020000100135803},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C111065885","wikidata":"https://www.wikidata.org/wiki/Q1189053","display_name":"Fuzz testing","level":3,"score":0.36230000853538513},{"id":"https://openalex.org/C39920170","wikidata":"https://www.wikidata.org/wiki/Q693083","display_name":"Soundness","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.32429999113082886},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2660999894142151}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/pst65910.2025.11268838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pst65910.2025.11268838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 22nd Annual International Conference on Privacy, Security, and Trust (PST)","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.polymtl.ca:71136","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401013","display_name":"PolyPublie (\u00c9cole Polytechnique de Montr\u00e9al)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45683168","host_organization_name":"Polytechnique Montr\u00e9al","host_organization_lineage":["https://openalex.org/I45683168"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1985987493","https://openalex.org/W2101786389","https://openalex.org/W2421957586","https://openalex.org/W2496959730","https://openalex.org/W2918664583","https://openalex.org/W2995988246","https://openalex.org/W3094485976","https://openalex.org/W4309674289","https://openalex.org/W4381331436","https://openalex.org/W4385245566","https://openalex.org/W4402352815","https://openalex.org/W4408147114"],"related_works":[],"abstract_inverted_index":{"Automated":[0],"penetration":[1],"testing":[2],"(AutoPT)":[3],"powered":[4,105],"by":[5,27,78,106,189],"large":[6],"language":[7],"models":[8],"(LLMs)":[9],"has":[10],"gained":[11],"attention":[12],"for":[13,48,133],"its":[14],"ability":[15],"to":[16,42,83,115,163],"automate":[17],"ethical":[18],"hacking":[19],"processes":[20],"and":[21,63,131,143,146],"identify":[22],"vulnerabilities":[23],"in":[24,45,55,59,119],"target":[25],"systems":[26],"leveraging":[28],"the":[29,51,60,69,73,121,125,155,165,185],"inherent":[30],"knowledge":[31,53],"of":[32,72,91,124],"LLMs.":[33],"However,":[34],"existing":[35,79],"LLM-based":[36],"AutoPT":[37,111],"frameworks":[38,80],"often":[39],"underperform":[40],"compared":[41],"human":[43,117],"experts":[44],"challenging":[46],"tasks":[47],"several":[49],"reasons:":[50],"imbalanced":[52],"used":[54],"LLM":[56],"training,":[57],"short-sightedness":[58],"planning":[61],"process,":[62,127],"hallucinations":[64],"during":[65],"command":[66],"generation.":[67],"Moreover,":[68],"trial-and-error":[70],"nature":[71],"PT":[74,92,103,126,156,193,202],"process":[75,157],"is":[76,113],"constrained":[77],"lacking":[81],"mechanisms":[82],"learn":[84],"from":[85,148],"previous":[86,149],"failures,":[87],"restricting":[88],"adaptive":[89],"improvement":[90],"strategies.":[93],"To":[94],"address":[95],"these":[96],"limitations,":[97],"we":[98],"propose":[99],"a":[100,159],"knowledge-informed,":[101],"selfreflective":[102],"framework":[104,112,167],"LLMs,":[107],"called":[108],"RefPentester.":[109],"This":[110],"designed":[114],"assist":[116],"operators":[118],"identifying":[120],"current":[122],"stage":[123,203],"selecting":[128],"appropriate":[129],"tactics":[130],"techniques":[132],"each":[134],"stage,":[135],"choosing":[136],"suggested":[137],"actions,":[138],"providing":[139],"step-by-step":[140],"operational":[141],"guidance,":[142],"reflecting":[144],"on":[145,178,201],"learning":[147],"failed":[150],"operations.":[151],"We":[152],"also":[153,196],"modeled":[154],"as":[158],"seven-state":[160],"Stage":[161],"Machine":[162],"integrate":[164],"proposed":[166],"effectively.":[168],"The":[169,180],"evaluation":[170],"shows":[171],"that":[172],"RefPentester":[173,195],"can":[174],"successfully":[175],"reveal":[176],"credentials":[177],"Hack":[179],"Box\u2019s":[181],"Sau":[182],"machine,":[183],"outperforming":[184],"baseline":[186],"GPT40":[187],"model":[188],"$16.7":[190],"\\%$.":[191],"Across":[192],"stages,":[194],"demonstrates":[197],"superior":[198],"success":[199],"rates":[200],"transitions.":[204]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-12-03T00:00:00"}