{"id":"https://openalex.org/W4415004355","doi":"https://doi.org/10.1109/acit65614.2025.11185806","title":"Email Augmentation: A Comparison of Fine-tuned Small Language Models","display_name":"Email Augmentation: A Comparison of Fine-tuned Small Language Models","publication_year":2025,"publication_date":"2025-09-17","ids":{"openalex":"https://openalex.org/W4415004355","doi":"https://doi.org/10.1109/acit65614.2025.11185806"},"language":"en","primary_location":{"id":"doi:10.1109/acit65614.2025.11185806","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acit65614.2025.11185806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 15th International Conference on Advanced Computer Information Technologies (ACIT)","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/A5082796012","display_name":"Francisco Cardoso","orcid":"https://orcid.org/0000-0002-4238-0772"},"institutions":[{"id":"https://openalex.org/I83863532","display_name":"Polytechnic Institute of Porto","ror":"https://ror.org/04988re48","country_code":"PT","type":"education","lineage":["https://openalex.org/I83863532"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Francisco Cardoso","raw_affiliation_strings":["GECAD, ISEP Polytechnic of Porto,Porto,Portugal"],"affiliations":[{"raw_affiliation_string":"GECAD, ISEP Polytechnic of Porto,Porto,Portugal","institution_ids":["https://openalex.org/I83863532"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004608532","display_name":"Eva Maia","orcid":"https://orcid.org/0000-0002-8075-531X"},"institutions":[{"id":"https://openalex.org/I83863532","display_name":"Polytechnic Institute of Porto","ror":"https://ror.org/04988re48","country_code":"PT","type":"education","lineage":["https://openalex.org/I83863532"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Eva Maia","raw_affiliation_strings":["GECAD, ISEP Polytechnic of Porto,Porto,Portugal"],"affiliations":[{"raw_affiliation_string":"GECAD, ISEP Polytechnic of Porto,Porto,Portugal","institution_ids":["https://openalex.org/I83863532"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005516592","display_name":"Isabel Pra\u00e7a","orcid":"https://orcid.org/0000-0002-2519-9859"},"institutions":[{"id":"https://openalex.org/I83863532","display_name":"Polytechnic Institute of Porto","ror":"https://ror.org/04988re48","country_code":"PT","type":"education","lineage":["https://openalex.org/I83863532"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Isabel Pra\u00e7a","raw_affiliation_strings":["GECAD, ISEP Polytechnic of Porto,Porto,Portugal"],"affiliations":[{"raw_affiliation_string":"GECAD, ISEP Polytechnic of Porto,Porto,Portugal","institution_ids":["https://openalex.org/I83863532"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082796012"],"corresponding_institution_ids":["https://openalex.org/I83863532"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27807681,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"491","last_page":"496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12607","display_name":"Personal Information Management and User Behavior","score":0.9825000166893005,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12607","display_name":"Personal Information Management and User Behavior","score":0.9825000166893005,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11122","display_name":"Online Learning and Analytics","score":0.9487000107765198,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9478999972343445,"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/phishing","display_name":"Phishing","score":0.9002000093460083},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6814000010490417},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6625999808311462},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6111999750137329},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5404999852180481},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.3783000111579895},{"id":"https://openalex.org/keywords/information-sensitivity","display_name":"Information sensitivity","score":0.36309999227523804}],"concepts":[{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.9002000093460083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8069000244140625},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6814000010490417},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6625999808311462},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6111999750137329},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5404999852180481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47929999232292175},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4611000120639801},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3465000092983246},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3091999888420105},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30469998717308044},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acit65614.2025.11185806","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acit65614.2025.11185806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 15th International Conference on Advanced Computer Information Technologies (ACIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"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":{"The":[0,113],"reliance":[1],"on":[2,60,122],"outdated":[3],"datasets":[4,37],"poses":[5],"significant":[6],"challenges":[7],"for":[8,84,142],"modern":[9],"phishing":[10,35,62,85],"detection":[11],"systems,":[12],"as":[13],"they":[14],"fail":[15],"to":[16,44,77,131,133],"capture":[17],"the":[18,116,125,138,143],"linguistic":[19],"diverse":[20,102],"and":[21,56,63,81,101,137],"contextual":[22],"relevance":[23],"of":[24,118,127,140,145],"AI":[25],"generated":[26,98],"email":[27,36,48,65,146],"messages.":[28,66],"To":[29],"address":[30],"this":[31],"we":[32],"propose":[33],"augmenting":[34],"using":[38],"fine-tuned":[39],"small":[40],"language":[41],"models":[42,108],"(SLMs)":[43],"generate":[45],"adaptable,":[46],"privacy-preserving":[47],"templates.":[49,147],"We":[50],"evaluate":[51],"two":[52],"SLMs\u2014GPT-2":[53],"(1.5B":[54],"parameters)":[55],"Gemma3":[57,97],"(1B":[58],"parameters)\u2014fine-tuned":[59],"preprocessed":[61],"benign":[64,105],"Our":[67],"approach":[68],"combines":[69],"template":[70],"generation":[71,86,144],"via":[72],"structured":[73],"prompts":[74],"with":[75,93],"preprocessing":[76],"anonymise":[78],"sensitive":[79],"data":[80],"fine-tuning.":[82],"Results":[83],"showed":[87],"that":[88],"GPT-2":[89],"achieves":[90],"higher":[91],"alignment":[92],"reference":[94],"templates,":[95],"while":[96],"more":[99],"novel":[100],"outputs.":[103],"For":[104],"emails,":[106],"both":[107],"achieved":[109],"very":[110],"similar":[111],"results.":[112],"findings":[114],"highlight":[115],"importance":[117],"model":[119],"selection":[120],"based":[121],"use-case":[123],"priorities,":[124],"usage":[126],"fine-tuning":[128],"in":[129],"addition":[130],"prompting":[132],"mitigate":[134],"privacy":[135],"risks":[136],"viability":[139],"SLMs":[141]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}