{"id":"https://openalex.org/W4415034621","doi":"https://doi.org/10.1109/scam67354.2025.00014","title":"Smelling Secrets: Leveraging Machine Learning and Language Models for Sensitive Parameter Detection in Ansible Security Analysis","display_name":"Smelling Secrets: Leveraging Machine Learning and Language Models for Sensitive Parameter Detection in Ansible Security Analysis","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W4415034621","doi":"https://doi.org/10.1109/scam67354.2025.00014"},"language":"en","primary_location":{"id":"doi:10.1109/scam67354.2025.00014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/scam67354.2025.00014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Source Code Analysis & Manipulation (SCAM)","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/A5084032561","display_name":"Ruben Opdebeeck","orcid":"https://orcid.org/0000-0002-0938-4843"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Ruben Opdebeeck","raw_affiliation_strings":["Vrije Universiteit,Software Languages Lab,Brussel,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit,Software Languages Lab,Brussel,Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053602609","display_name":"Valeria Pontillo","orcid":"https://orcid.org/0000-0001-6012-9947"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Valeria Pontillo","raw_affiliation_strings":["Vrije Universiteit,Software Languages Lab,Brussel,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit,Software Languages Lab,Brussel,Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090206652","display_name":"Camilo Vel\u00e1zquez-Rodr\u00edguez","orcid":"https://orcid.org/0000-0002-8360-1519"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Camilo Vel\u00e1zquez-Rodr\u00edguez","raw_affiliation_strings":["Vrije Universiteit,Software Languages Lab,Brussel,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit,Software Languages Lab,Brussel,Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090657641","display_name":"Wolfgang De Meuter","orcid":"https://orcid.org/0000-0002-5229-5627"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Wolfgang De Meuter","raw_affiliation_strings":["Vrije Universiteit,Software Languages Lab,Brussel,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit,Software Languages Lab,Brussel,Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042827940","display_name":"Coen De Roover","orcid":"https://orcid.org/0000-0002-1710-1268"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Coen De Roover","raw_affiliation_strings":["Vrije Universiteit,Software Languages Lab,Brussel,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit,Software Languages Lab,Brussel,Belgium","institution_ids":["https://openalex.org/I13469542"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29586544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"77"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.7828999757766724,"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"}},"topics":[{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.7828999757766724,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.730400025844574,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.6527000069618225,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.6730999946594238},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.6650000214576721},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6625999808311462},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.605400025844574},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4641999900341034},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46070000529289246},{"id":"https://openalex.org/keywords/true-positive-rate","display_name":"True positive rate","score":0.4259999990463257},{"id":"https://openalex.org/keywords/false-positives-and-false-negatives","display_name":"False positives and false negatives","score":0.41749998927116394},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4171999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8054999709129333},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.6730999946594238},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6672000288963318},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.6650000214576721},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6625999808311462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6402999758720398},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.605400025844574},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4641999900341034},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C2989486834","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"True positive rate","level":2,"score":0.4259999990463257},{"id":"https://openalex.org/C112789634","wikidata":"https://www.wikidata.org/wiki/Q18207010","display_name":"False positives and false negatives","level":3,"score":0.41749998927116394},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.41280001401901245},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3824999928474426},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37689998745918274},{"id":"https://openalex.org/C109297577","wikidata":"https://www.wikidata.org/wiki/Q161157","display_name":"Password","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.3327000141143799},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.296999990940094},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/scam67354.2025.00014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/scam67354.2025.00014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Source Code Analysis & Manipulation (SCAM)","raw_type":"proceedings-article"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:261940","is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/smelling-secrets-leveraging-machine-learning-and-language-models-for-sensitive-parameter-detection-in-ansible-security-analysis(6de7df0e-d7ee-4e9d-9493-c0b9e7f1e9f5).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"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":"publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4881123832","display_name":null,"funder_award_id":"S000323N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1964940342","https://openalex.org/W1993220166","https://openalex.org/W2078197322","https://openalex.org/W2112081648","https://openalex.org/W2140964565","https://openalex.org/W2149706766","https://openalex.org/W2395579298","https://openalex.org/W2796047065","https://openalex.org/W2807298173","https://openalex.org/W2883411629","https://openalex.org/W2900918122","https://openalex.org/W2921496954","https://openalex.org/W2955656327","https://openalex.org/W2961642335","https://openalex.org/W2963846996","https://openalex.org/W2963995913","https://openalex.org/W2993710525","https://openalex.org/W3010949534","https://openalex.org/W3034850762","https://openalex.org/W3104902066","https://openalex.org/W3106029585","https://openalex.org/W3118657661","https://openalex.org/W3123074563","https://openalex.org/W4253731935","https://openalex.org/W4281557843","https://openalex.org/W4282924800","https://openalex.org/W4284664377","https://openalex.org/W4291213652","https://openalex.org/W4297254899","https://openalex.org/W4307811449","https://openalex.org/W4313563645","https://openalex.org/W4318594359","https://openalex.org/W4384009698","https://openalex.org/W4384211300","https://openalex.org/W4385245566","https://openalex.org/W4388483564","https://openalex.org/W4391558373","https://openalex.org/W4400582494","https://openalex.org/W4400762160","https://openalex.org/W4402455229","https://openalex.org/W4402670856","https://openalex.org/W4403223353","https://openalex.org/W4410553379","https://openalex.org/W4411337520"],"related_works":[],"abstract_inverted_index":{"Infrastructure":[0,14],"as":[1,21],"Code":[2],"is":[3],"an":[4],"emerging":[5],"paradigm":[6],"to":[7,31,38,56,62,81,154,165,195,212,232,238,242],"automate":[8],"the":[9,68,90,126,157,170,183,188,205,213,217,228,233,257,267,270],"configuration":[10],"of":[11,45,70,89,99,152,159,163,272],"cloud":[12],"infrastructures.":[13],"code":[15],"often":[16],"processes":[17],"secret":[18,115],"information,":[19],"such":[20,27],"passwords":[22],"or":[23],"private":[24],"keys.":[25],"Mishandling":[26],"secrets":[28,262],"can":[29],"lead":[30],"information":[32],"disclosure":[33],"vulnerabilities,":[34],"yet":[35],"existing":[36],"efforts":[37],"detect":[39],"them":[40],"rely":[41],"on":[42,182,274],"pattern":[43],"matching":[44],"parameter":[46],"and":[47,53,75,105,123,179,192],"variable":[48],"names,":[49],"causing":[50],"false":[51,244],"positives":[52,245],"negatives":[54],"due":[55],"suboptimal":[57],"string":[58,200],"patterns.This":[59],"paper":[60],"aims":[61],"address":[63],"these":[64],"limitations":[65],"by":[66,249,264],"assessing":[67],"effectiveness":[69],"traditional":[71],"Machine":[72],"Learning":[73],"(ML)":[74],"transformer-based":[76],"Language":[77],"Model":[78],"(LM)":[79],"classifiers":[80,194],"predict":[82],"sensitive":[83],"module":[84,103],"parameters":[85,104,112],"in":[86,174,246,266],"Ansible,":[87],"one":[88],"most":[91],"popular":[92],"IaC":[93],"tools.":[94],"We":[95,167,202],"collect":[96],"a":[97,150,160,209,275],"dataset":[98],"over":[100],"160,000":[101],"Ansible":[102],"their":[106],"documentation,":[107],"containing":[108],"more":[109],"than":[110],"16,000":[111],"that":[113,125,198,204,227,256],"expect":[114],"data.":[116],"Then,":[117],"we":[118,141,253],"train":[119],"several":[120,261],"ML":[121,191,206],"algorithms":[122],"find":[124,203,255],"Random":[127],"Forest":[128],"algorithm":[129],"performs":[130],"best,":[131],"achieving":[132],"93.5%":[133],"precision":[134,162,177],"but":[135],"limited":[136],"recall":[137,151,180],"(72.7%).":[138],"In":[139],"parallel,":[140],"evaluate":[142],"multiple":[143],"pretrained":[144],"zero-shot":[145],"language":[146,171],"models,":[147,172],"which":[148],"achieve":[149],"up":[153,164],"90.4%":[155],"at":[156],"expense":[158],"lower":[161],"88.5%.":[166],"subsequently":[168],"fine-tune":[169],"resulting":[173],"nearly":[175],"perfect":[176],"(99.8%)":[178,181],"ground":[184,277],"truth":[185],"dataset.We":[186],"compare":[187],"best":[189],"performing":[190],"LM":[193,219,259],"two":[196,214],"baselines":[197],"use":[199,239],"patterns.":[201],"classifier":[207],"achieves":[208],"performance":[210],"comparable":[211],"baselines,":[215,234],"while":[216],"fine-tuned":[218,258],"outperforms":[220],"all":[221],"approaches.":[222],"A":[223],"qualitative":[224],"comparison":[225],"reveals":[226],"approaches":[229],"are":[230],"complementary":[231],"motivating":[235],"future":[236],"work":[237],"prediction":[240],"models":[241],"reduce":[243],"reports":[247],"generated":[248],"inexpensive":[250],"baselines.":[251],"However,":[252],"also":[254],"misses":[260],"caused":[263],"noise":[265],"dataset,":[268],"highlighting":[269],"importance":[271],"fine-tuning":[273],"high-quality":[276],"truth.":[278]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}