{"id":"https://openalex.org/W7154696045","doi":"https://doi.org/10.1109/access.2026.3685036","title":"CONV_GBERT: Leveraging BERT\u2013GPT Fusion and IMP-FGSM for Adversarially Robust Sentiment Classification","display_name":"CONV_GBERT: Leveraging BERT\u2013GPT Fusion and IMP-FGSM for Adversarially Robust Sentiment Classification","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7154696045","doi":"https://doi.org/10.1109/access.2026.3685036"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3685036","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3685036","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.2026.3685036","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133906739","display_name":"Areeba Umair","orcid":"https://orcid.org/0000-0003-3638-7369"},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Areeba Umair","raw_affiliation_strings":["Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, Italy"],"raw_orcid":"https://orcid.org/0000-0003-3638-7369","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, Italy","institution_ids":["https://openalex.org/I71267560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005904043","display_name":"Elio Masciari","orcid":"https://orcid.org/0000-0002-1778-5321"},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elio Masciari","raw_affiliation_strings":["Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, Italy"],"raw_orcid":"https://orcid.org/0000-0002-1778-5321","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, Italy","institution_ids":["https://openalex.org/I71267560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006599220","display_name":"Muhammad Habib Ullah","orcid":"https://orcid.org/0000-0003-0580-9207"},"institutions":[{"id":"https://openalex.org/I4210125249","display_name":"Istituto per il Rilevamento Elettromagnetico dell'Ambiente","ror":"https://ror.org/02wxw4x45","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210125249","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Muhammad Habib Ullah","raw_affiliation_strings":["National Research Council of Italy (CNR), Institute for Electromagnetic Sensing of the Environment (IREA), Naples, Italy"],"raw_orcid":"https://orcid.org/0000-0003-0580-9207","affiliations":[{"raw_affiliation_string":"National Research Council of Italy (CNR), Institute for Electromagnetic Sensing of the Environment (IREA), Naples, Italy","institution_ids":["https://openalex.org/I4210155236","https://openalex.org/I4210125249"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.43856643,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"64427","last_page":"64439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.43860000371932983,"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":0.43860000371932983,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.19210000336170197,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.09279999881982803,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.48350000381469727},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4560999870300293},{"id":"https://openalex.org/keywords/information-fusion","display_name":"Information fusion","score":0.3643999993801117},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33880001306533813},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3386000096797943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670999765396118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5817000269889832},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.48350000381469727},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4560999870300293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3700000047683716},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3668000102043152},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3386000096797943},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3685036","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3685036","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:a52b1a7acb994432b0146a91ecd79d8d","is_oa":true,"landing_page_url":"https://doaj.org/article/a52b1a7acb994432b0146a91ecd79d8d","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 64427-64439 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3685036","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3685036","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,95],"paper":[1],"introduces":[2,81],"CONV_GBERT,":[3],"a":[4,48],"hybrid":[5],"deep":[6],"learning":[7],"framework":[8],"for":[9,77],"robust":[10],"sentiment":[11,59,112,154],"classification.":[12],"The":[13],"model":[14],"integrates":[15],"the":[16,22,28,85,98,142],"bidirectional":[17],"contextual":[18],"understanding":[19],"of":[20,25,33,125,128,131,137,144],"BERT,":[21],"generative":[23],"capabilities":[24],"GPT,":[26],"and":[27,42,44,57,67,88,133,149,159],"local":[29],"feature":[30],"extraction":[31],"strength":[32],"convolutional":[34,49],"neural":[35],"networks.":[36],"By":[37],"concatenating":[38],"embeddings":[39,87],"from":[40],"BERT":[41],"GPT":[43],"passing":[45],"them":[46,91],"through":[47],"layer,":[50],"CONV_GBERT":[51,116],"captures":[52],"both":[53],"global":[54],"semantic":[55],"meaning":[56],"fine-grained":[58],"patterns":[60],"in":[61,156],"text.":[62],"To":[63],"further":[64],"enhance":[65],"robustness":[66],"generalization,":[68],"we":[69],"incorporate":[70],"Improved":[71],"Fast":[72],"Gradient":[73],"Sign":[74],"Method":[75],"(IMP-FGSM)":[76],"adversarial":[78,102,150],"training.":[79],"IMP-FGSM":[80],"controlled":[82],"perturbations":[83],"to":[84,101,152],"input":[86],"iteratively":[89],"refines":[90],"using":[92],"gradient-based":[93],"updates.":[94],"technique":[96],"improves":[97],"model\u2019s":[99],"resistance":[100],"attacks":[103],"while":[104],"preserving":[105],"valid":[106],"token":[107],"boundaries.":[108],"Experiments":[109],"on":[110],"benchmark":[111],"datasets":[113],"demonstrate":[114],"that":[115],"significantly":[117],"outperforms":[118],"baseline":[119],"models.":[120],"It":[121],"achieves":[122],"an":[123,134],"accuracy":[124],"84.89%,":[126],"precision":[127],"83.67%,":[129],"recall":[130],"82.88%,":[132],"F1":[135],"score":[136],"83.37%.":[138],"These":[139],"results":[140],"highlight":[141],"potential":[143],"combining":[145],"multiple":[146],"transformer-based":[147],"architectures":[148],"training":[151],"advance":[153],"analysis":[155],"complex,":[157],"noisy,":[158],"dynamic":[160],"textual":[161],"environments.":[162]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2026-04-18T00:00:00"}