{"id":"https://openalex.org/W7133209619","doi":"https://doi.org/10.1109/access.2026.3669713","title":"Toward a Secure Future: An Integrated Framework for PII Detection Using NLP and Visual Analysis","display_name":"Toward a Secure Future: An Integrated Framework for PII Detection Using NLP and Visual Analysis","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7133209619","doi":"https://doi.org/10.1109/access.2026.3669713"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3669713","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3669713","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3669713","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"S. Sheela","orcid":"https://orcid.org/0000-0002-7951-579X"},"institutions":[{"id":"https://openalex.org/I4387153738","display_name":"Siddaganga Institute of Technology","ror":"https://ror.org/00wd8c661","country_code":"IN","type":"education","lineage":["https://openalex.org/I4387153738"]},{"id":"https://openalex.org/I510634243","display_name":"Sri Siddhartha Medical College","ror":"https://ror.org/01zemh668","country_code":"IN","type":"education","lineage":["https://openalex.org/I4403386631","https://openalex.org/I510634243"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"S. Sheela","raw_affiliation_strings":["Department of CSE, Siddaganga Institute of Technology, Tumakuru, India"],"raw_orcid":"https://orcid.org/0000-0002-7951-579X","affiliations":[{"raw_affiliation_string":"Department of CSE, Siddaganga Institute of Technology, Tumakuru, India","institution_ids":["https://openalex.org/I510634243","https://openalex.org/I4387153738"]}]},{"author_position":"middle","author":{"id":null,"display_name":"P. S. Akshatha","orcid":"https://orcid.org/0000-0003-1319-2753"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P. S. Akshatha","raw_affiliation_strings":["Department of Artificial Intelligence and Machine Learning, New Horizon College of Engineering, Bengaluru, India"],"raw_orcid":"https://orcid.org/0000-0003-1319-2753","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence and Machine Learning, New Horizon College of Engineering, Bengaluru, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"M. R. Kushalatha","orcid":"https://orcid.org/0000-0002-4192-2242"},"institutions":[{"id":"https://openalex.org/I1333540553","display_name":"Nitte University","ror":"https://ror.org/029nydt37","country_code":"IN","type":"education","lineage":["https://openalex.org/I1333540553"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"M. R. Kushalatha","raw_affiliation_strings":["Department of ECE, Nitte Meenakshi Institute of Technology, Nitte (Deemed to be University), Bengaluru, India"],"raw_orcid":"https://orcid.org/0000-0002-4192-2242","affiliations":[{"raw_affiliation_string":"Department of ECE, Nitte Meenakshi Institute of Technology, Nitte (Deemed to be University), Bengaluru, India","institution_ids":["https://openalex.org/I1333540553"]}]},{"author_position":"last","author":{"id":null,"display_name":"S. M. Dilip Kumar","orcid":"https://orcid.org/0000-0002-0541-4419"},"institutions":[{"id":"https://openalex.org/I65674248","display_name":"Visvesvaraya Technological University","ror":"https://ror.org/00ha14p11","country_code":"IN","type":"education","lineage":["https://openalex.org/I65674248"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. M. Dilip Kumar","raw_affiliation_strings":["Department of CSE, University of Visvesvaraya College of Engineering, Bengaluru, India"],"raw_orcid":"https://orcid.org/0000-0002-0541-4419","affiliations":[{"raw_affiliation_string":"Department of CSE, University of Visvesvaraya College of Engineering, Bengaluru, India","institution_ids":["https://openalex.org/I65674248"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4387153738","https://openalex.org/I510634243"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37606504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"36401","last_page":"36413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12572","display_name":"Intelligence, Security, War Strategy","score":0.04899999871850014,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12572","display_name":"Intelligence, Security, War Strategy","score":0.04899999871850014,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.028200000524520874,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T13055","display_name":"Global Security and Public Health","score":0.02710000053048134,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/authentication","display_name":"Authentication (law)","score":0.47200000286102295},{"id":"https://openalex.org/keywords/safeguarding","display_name":"Safeguarding","score":0.4715000092983246},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.46959999203681946},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.45910000801086426},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.45509999990463257},{"id":"https://openalex.org/keywords/bitmap","display_name":"Bitmap","score":0.4156999886035919},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.3605000078678131},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.35089999437332153},{"id":"https://openalex.org/keywords/message-authentication-code","display_name":"Message authentication code","score":0.3434999883174896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8669000267982483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5139999985694885},{"id":"https://openalex.org/C148417208","wikidata":"https://www.wikidata.org/wiki/Q4825882","display_name":"Authentication (law)","level":2,"score":0.47200000286102295},{"id":"https://openalex.org/C2776743756","wikidata":"https://www.wikidata.org/wiki/Q5097921","display_name":"Safeguarding","level":2,"score":0.4715000092983246},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.46959999203681946},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.45910000801086426},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.45509999990463257},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4165000021457672},{"id":"https://openalex.org/C3115412","wikidata":"https://www.wikidata.org/wiki/Q1194708","display_name":"Bitmap","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3935000002384186},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3817000091075897},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36090001463890076},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3605000078678131},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C141492731","wikidata":"https://www.wikidata.org/wiki/Q1052621","display_name":"Message authentication code","level":3,"score":0.3434999883174896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C527648132","wikidata":"https://www.wikidata.org/wiki/Q189900","display_name":"Information security","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27790001034736633},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C118463975","wikidata":"https://www.wikidata.org/wiki/Q220849","display_name":"Digital signature","level":3,"score":0.2694000005722046},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C84418412","wikidata":"https://www.wikidata.org/wiki/Q3246940","display_name":"Digital forensics","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C42781572","wikidata":"https://www.wikidata.org/wiki/Q1250322","display_name":"Digital image","level":4,"score":0.2606000006198883},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C556601545","wikidata":"https://www.wikidata.org/wiki/Q878553","display_name":"Computer forensics","level":3,"score":0.2563999891281128},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3669713","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3669713","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a93828ef891743a680dafa347211f856","is_oa":true,"landing_page_url":"https://doaj.org/article/a93828ef891743a680dafa347211f856","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 36401-36413 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3669713","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3669713","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4724646508693695,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2933382925","https://openalex.org/W2964361219","https://openalex.org/W3217675075","https://openalex.org/W4285791949","https://openalex.org/W4376867987","https://openalex.org/W4385679821","https://openalex.org/W4386128187","https://openalex.org/W4387951913","https://openalex.org/W4388937569","https://openalex.org/W4390337419","https://openalex.org/W4391092855","https://openalex.org/W4392554186","https://openalex.org/W4401748255","https://openalex.org/W4404793717","https://openalex.org/W4407264610","https://openalex.org/W4407360992","https://openalex.org/W4408358984","https://openalex.org/W4408472883","https://openalex.org/W4411853425"],"related_works":[],"abstract_inverted_index":{"Safeguarding":[0],"Personally":[1],"Identifiable":[2],"Information":[3],"(PII)":[4],"is":[5,85,172],"critical":[6],"to":[7,174,213],"prevent":[8],"data":[9],"breaches":[10],"and":[11,27,41,56,76,113,178,185,189,199,209],"identity":[12,201],"theft":[13],"in":[14,181],"the":[15,63,88,102,131,182,207,214],"era":[16],"of":[17,108,128,141,159],"digital":[18],"services.":[19],"This":[20,193],"paper":[21],"presents":[22],"a":[23,42,92,98],"hybrid":[24,119],"PII":[25,58,95,148,160,191],"detection":[26,59,68,180],"secure":[28,190],"verification":[29,202],"system":[30,166],"that":[31,87,204],"integrates":[32],"rule-based":[33],"regular":[34],"expressions,":[35],"transformer-based":[36],"spaCy":[37],"NLP,":[38],"BERT":[39,114],"models,":[40],"Swin":[43,64,132],"Transformer-based":[44],"FasterRCNN":[45],"pipeline.":[46],"While":[47],"text-based":[48],"methods":[49],"(Regex,":[50],"SpaCy,":[51],"BERT)":[52],"excel":[53],"at":[54],"structured":[55],"contextual":[57],"from":[60],"OCR-processed":[61],"text,":[62],"Transformer":[65,133],"provides":[66,156,195],"vision-based":[67,179],"capability":[69],"for":[70,146,187],"document":[71],"images,":[72],"handling":[73],"complex":[74],"layouts":[75],"visual":[77],"cues":[78],"often":[79],"missed":[80],"by":[81],"traditional":[82],"pipelines.":[83],"It":[84],"observed":[86],"empirical":[89],"evaluation":[90],"on":[91],"synthetic":[93],"Indian":[94],"dataset":[96],"shows":[97],"significant":[99],"performance":[100,145],"improvement:":[101],"Regex":[103],"method":[104],"achieves":[105,116],"an":[106,125,139,196],"F1-score":[107,127,140],"0.445,":[109],"spacy":[110],"reaches":[111],"0.166,":[112],"alone":[115],"0.042.":[117],"The":[118],"model,":[120],"which":[121],"combines":[122],"these,":[123],"yields":[124],"improved":[126],"0.515,":[129],"while":[130,162],"model":[134],"outperforms":[135],"all":[136],"others":[137],"with":[138],"0.978,":[142],"demonstrating":[143],"near-perfect":[144],"image-based":[147],"detection.":[149],"A":[150],"blockchain-backed":[151],"double":[152],"hashing":[153],"mechanism,":[154],"SHA-256,":[155],"tamper-proof":[157],"storage":[158],"fingerprints,":[161],"OTPbased":[163],"authentication":[164],"secures":[165],"access.":[167],"In":[168],"this":[169],"work,":[170],"it":[171],"proposed":[173],"use":[175],"both":[176],"OCR":[177],"scanned":[183],"PDFs":[184],"images":[186],"robust":[188],"verification.":[192],"framework":[194],"interpretable,":[197],"scalable,":[198],"privacy-preserving":[200],"solution":[203],"improves":[205],"upon":[206],"accuracy":[208],"layout":[210],"awareness":[211],"compared":[212],"previous":[215],"methods.":[216]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2026-03-03T00:00:00"}