{"id":"https://openalex.org/W7225459743","doi":"https://doi.org/10.5281/zenodo.24030035","title":"Machine Learning Based Data Leakage Detection and Prevention","display_name":"Machine Learning Based Data Leakage Detection and Prevention","publication_year":2026,"publication_date":"2026-11-07","ids":{"openalex":"https://openalex.org/W7225459743","doi":"https://doi.org/10.5281/zenodo.24030035"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24030035","doi":"https://doi.org/10.5281/zenodo.24030035","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24030035","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24030035","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102865569","display_name":"Harshita Jain","orcid":"https://orcid.org/0000-0002-7492-7779","observed_orcids":["https://orcid.org/0000-0002-7492-7779"]},"institutions":[{"id":"https://openalex.org/I119668213","display_name":"Karunya University","ror":"https://ror.org/03k23nv15","country_code":"IN","type":"education","lineage":["https://openalex.org/I119668213"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Harshita Jain","raw_affiliation_strings":["KITS, Ramtek"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KITS, Ramtek","institution_ids":["https://openalex.org/I119668213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161186140","display_name":"Vishakha Belge","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vishakha Belge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161181934","display_name":"Vivek Kurve","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vivek Kurve","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161251088","display_name":"Tanmay Gharde","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tanmay Gharde","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161164138","display_name":"Savi Sawwalakhe","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Savi Sawwalakhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5161183996","display_name":"Vedant Matte","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vedant Matte","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10734","display_name":"Information and Cyber Security","score":0.3596000075340271,"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"}},"topics":[{"id":"https://openalex.org/T10734","display_name":"Information and Cyber Security","score":0.3596000075340271,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.1914999932050705,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.15189999341964722,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-leakage-detection","display_name":"data leakage detection","score":0.9909999966621399},{"id":"https://openalex.org/keywords/data-loss-prevention","display_name":"data loss prevention","score":0.9259999990463257},{"id":"https://openalex.org/keywords/tf-idf","display_name":"TF-IDF","score":0.722000002861023},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"logistic regression","score":0.9890000224113464},{"id":"https://openalex.org/keywords/isolation-forest","display_name":"Isolation Forest","score":0.8970000147819519},{"id":"https://openalex.org/keywords/security-policy-management","display_name":"security policy management","score":0.6240000128746033}],"concepts":[{"id":"https://openalex.org/C507366226","wikidata":"https://www.wikidata.org/wiki/Q42378","display_name":"USB","level":3,"score":0.732699990272522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6403999924659729},{"id":"https://openalex.org/C2779201187","wikidata":"https://www.wikidata.org/wiki/Q2775060","display_name":"Information leakage","level":2,"score":0.5296000242233276},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.49129998683929443},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3978999853134155},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3765999972820282},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C70236469","wikidata":"https://www.wikidata.org/wiki/Q1078262","display_name":"Database administrator","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3346000015735626},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C2780814629","wikidata":"https://www.wikidata.org/wiki/Q327353","display_name":"System administrator","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3248000144958496},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29280000925064087},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2919999957084656},{"id":"https://openalex.org/C35525427","wikidata":"https://www.wikidata.org/wiki/Q745881","display_name":"Intrusion detection system","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2754000127315521},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.26980000734329224},{"id":"https://openalex.org/C2778579508","wikidata":"https://www.wikidata.org/wiki/Q722192","display_name":"System call","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C2778717966","wikidata":"https://www.wikidata.org/wiki/Q4189076","display_name":"Protection mechanism","level":3,"score":0.258899986743927},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24030035","doi":"https://doi.org/10.5281/zenodo.24030035","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24030035","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},{"id":"doi:10.5281/zenodo.24030036","doi":"https://doi.org/10.5281/zenodo.24030036","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24030036","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24030035","doi":"https://doi.org/10.5281/zenodo.24030035","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24030035","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3089135706","https://openalex.org/W4410847668","https://openalex.org/W7203746182","https://openalex.org/W2246773685","https://openalex.org/W2020562427","https://openalex.org/W4385713434","https://openalex.org/W2171536910","https://openalex.org/W7214350815","https://openalex.org/W4391266482","https://openalex.org/W7217539820"],"abstract_inverted_index":{"Data":[0],"leakage":[1,28,237],"refers":[2],"to":[3,97,148,157,199,225],"the":[4,136,141,168,201,207,212],"unauthorized":[5],"disclosure":[6],"or":[7],"unintended":[8],"transfer":[9,120],"of":[10,203,214],"sensitive":[11,116],"information":[12],"and":[13,30,44,69,87,94,101,107,192,211,231,239],"represents":[14],"a":[15,25,125,178],"significant":[16],"security":[17],"concern":[18],"for":[19,34,47,62,114,235],"organizations.":[20],"This":[21],"paper":[22],"presents":[23],"SentinelDLP,":[24],"machine-learning-based":[26],"data":[27,236],"detection":[29,70,238],"prevention":[31,111,182,215,233],"system":[32,38,91],"designed":[33],"Windows":[35,161],"endpoints.":[36],"The":[37,90,160,184,220],"combines":[39],"rule-based":[40],"techniques":[41],"with":[42,132],"TF-IDF":[43],"Logistic":[45],"Regression":[46],"content":[48,227],"classification":[49],"into":[50],"different":[51],"sensitivity":[52],"levels.":[53],"It":[54,103],"also":[55,104],"includes":[56],"an":[57,223],"Isolation":[58],"Forest":[59],"component":[60],"intended":[61],"behavioural":[63,204],"anomaly":[64,205],"detection.":[65],"SentinelDLP":[66],"provides":[67],"monitoring":[68,100],"capabilities":[71],"across":[72,216],"multiple":[73],"endpoint":[74,229],"channels,":[75],"including":[76],"filesystem":[77],"activity,":[78],"USB":[79,119,149],"devices,":[80,86],"clipboard":[81],"operations,":[82],"screenshots,":[83],"printing,":[84],"MTP":[85],"network":[88],"shares.":[89],"generates":[92],"alerts":[93],"incident":[95],"records":[96],"support":[98],"administrative":[99],"investigation.":[102],"incorporates":[105],"risk-scoring":[106],"policy-management":[108],"components.":[109],"Print":[110],"is":[112,122,165,197],"implemented":[113,175],"detected":[115],"printing":[117],"activities.":[118],"blocking":[121,154],"activated":[123],"through":[124],"separate":[126,190],"command":[127],"that":[128],"must":[129],"be":[130],"executed":[131],"administrator":[133],"privileges":[134],"from":[135],"project":[137,221],"directory.":[138],"Once":[139],"activated,":[140],"current":[142],"mechanism":[143],"blocks":[144],"all":[145,217],"file":[146],"transfers":[147],"devices":[150],"rather":[151],"than":[152],"selectively":[153],"files":[155],"according":[156],"their":[158],"sensitivity.":[159],"Shell":[162],"Copy":[163],"Hook":[164],"present":[166],"in":[167],"source":[169],"code":[170],"but":[171],"has":[172],"not":[173],"been":[174],"successfully":[176],"as":[177],"functioning":[179],"selective":[180],"file-copy":[181],"mechanism.":[183],"content-classification":[185],"model":[186],"was":[187],"evaluated":[188],"using":[189],"training":[191],"testing":[193],"datasets.":[194],"Further":[195],"verification":[196],"required":[198],"establish":[200],"integration":[202],"detection,":[206],"reported":[208],"evaluation":[209],"metrics,":[210],"effectiveness":[213],"monitored":[218],"channels.":[219],"demonstrates":[222],"approach":[224],"combining":[226],"classification,":[228],"monitoring,":[230],"selected":[232],"mechanisms":[234],"prevention.":[240]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-08T00:00:00"}