{"id":"https://openalex.org/W4409156605","doi":"https://doi.org/10.1109/trustcom63139.2024.00133","title":"Topic-Aware Sensitive Information Detection in Chinese Large Language Model","display_name":"Topic-Aware Sensitive Information Detection in Chinese Large Language Model","publication_year":2024,"publication_date":"2024-12-17","ids":{"openalex":"https://openalex.org/W4409156605","doi":"https://doi.org/10.1109/trustcom63139.2024.00133"},"language":"en","primary_location":{"id":"doi:10.1109/trustcom63139.2024.00133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/trustcom63139.2024.00133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 23rd International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5001632561","display_name":"Yalin Sun","orcid":"https://orcid.org/0000-0003-1414-8295"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yalin Sun","raw_affiliation_strings":["Xidian University,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University,Xi’an,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017220281","display_name":"Ruiying Lu","orcid":"https://orcid.org/0000-0002-8825-6064"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiying Lu","raw_affiliation_strings":["Xidian University,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University,Xi’an,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101905361","display_name":"Kang Li","orcid":"https://orcid.org/0000-0003-0748-1583"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang Li","raw_affiliation_strings":["Xidian University,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University,Xi’an,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107092573","display_name":"Yu Zheng","orcid":"https://orcid.org/0000-0003-0757-4210"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zheng","raw_affiliation_strings":["Xidian University,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University,Xi’an,China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":1.0668,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.81337012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"908","last_page":"915"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9550999999046326,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9550999999046326,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9301999807357788,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6505647897720337},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42404744029045105},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41365569829940796},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3206706643104553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6505647897720337},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42404744029045105},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41365569829940796},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3206706643104553}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/trustcom63139.2024.00133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/trustcom63139.2024.00133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 23rd International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W3009165665","https://openalex.org/W3124640783","https://openalex.org/W3127619158","https://openalex.org/W3128430473","https://openalex.org/W3130799191","https://openalex.org/W3137268797","https://openalex.org/W3153120079","https://openalex.org/W3191730131","https://openalex.org/W4221143572","https://openalex.org/W4367595583","https://openalex.org/W4385452929","https://openalex.org/W4385565446","https://openalex.org/W4389352564","https://openalex.org/W4402667010","https://openalex.org/W6662301289","https://openalex.org/W6838760792","https://openalex.org/W6850357939","https://openalex.org/W6852033271","https://openalex.org/W6857193164"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"With":[0],"the":[1,53,69,86,91,100,105,131,137,181,184,212,228,257],"rapid":[2],"advancement":[3],"of":[4,16,28,55,71,133,194,201,220,252],"deep":[5],"learning,":[6],"generative":[7,31,72],"AI":[8,32,73],"models":[9,249],"have":[10],"emerged":[11],"as":[12],"a":[13,65,78,117,162],"prominent":[14],"area":[15],"focus.":[17],"However,":[18],"these":[19],"developments":[20],"bring":[21],"potential":[22],"security":[23,33,37,70,101,229],"concerns.":[24],"China\u2019s":[25],"guiding":[26],"document":[27,106],"government":[29],"on":[30,227,256],"identifies":[34],"31":[35],"specific":[36,231],"risks":[38,102],"across":[39],"five":[40],"categories,":[41],"including":[42],"content":[43,61,157,203],"that":[44,150,244],"violates":[45],"socialist":[46],"core":[47],"values":[48],"and":[49,59,98,115,144,172,208,224,239,254],"discriminatory":[50],"content.":[51],"Detecting":[52],"sensitivity":[54],"both":[56],"user":[57],"input":[58],"model-generated":[60],"has":[62],"therefore":[63],"become":[64],"critical":[66],"challenge":[67],"for":[68,81,110,155],"models.":[74,94,236],"This":[75],"paper":[76],"proposes":[77],"robust":[79],"scheme":[80],"detecting":[82],"sensitive":[83,156,177,202],"information":[84,154,171,178],"in":[85,104,127,218,250],"Chinese":[87,121,195,233],"languages":[88],"generated":[89],"from":[90],"large":[92,234],"language":[93,235],"Initially,":[95],"we":[96,135,160],"detect":[97],"classify":[99],"outlined":[103],"\"Basic":[107],"Security":[108],"Requirements":[109],"Generative":[111],"Artificial":[112],"Intelligence":[113],"Service\"":[114],"develop":[116],"comprehensive":[118],"dataset,":[119],"named":[120],"Sensitive":[122],"Language":[123],"Detection":[124],"(CSLD).":[125],"Specifically,":[126],"order":[128],"to":[129,140,167,175,189,232],"leverage":[130],"semantics":[132],"languages,":[134],"introduce":[136],"topic":[138],"model":[139,246],"pre-analyze":[141],"text":[142],"data":[143,222],"construct":[145],"topic-augmented":[146],"classification":[147,200],"vectors":[148],"(TACV)":[149],"supply":[151],"effective":[152],"contextual":[153,170],"detection.":[158,179],"Additionally,":[159],"propose":[161],"topic-infused":[163],"attention":[164],"mechanism":[165],"(TIAM)":[166],"provide":[168],"richer":[169],"relevant":[173],"topics":[174],"guide":[176],"At":[180],"same":[182],"time,":[183],"proposed":[185,213],"framework":[186],"is":[187],"designed":[188],"integrate":[190],"with":[191],"various":[192],"classes":[193],"pre-trained":[196],"models,":[197],"enabling":[198],"accurate":[199],"while":[204],"maintaining":[205],"low":[206],"latency":[207],"memory":[209],"usage.":[210],"Furthermore,":[211],"dataset":[214],"surpasses":[215],"existing":[216,248],"ones":[217],"terms":[219,251],"coverage,":[221],"volume,":[223],"its":[225],"focus":[226],"challenges":[230],"Without":[237],"bells":[238],"whistles,":[240],"our":[241,245],"experiments":[242],"demonstrate":[243],"outperforms":[247],"accuracy":[253],"efficiency":[255],"CSLD":[258],"dataset.":[259]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}