{"id":"https://openalex.org/W7152417017","doi":"https://doi.org/10.1145/3774904.3792549","title":"PrivSniffer: Graph-based Contextual Privacy Leakage Detection for User-Generated Texts","display_name":"PrivSniffer: Graph-based Contextual Privacy Leakage Detection for User-Generated Texts","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152417017","doi":"https://doi.org/10.1145/3774904.3792549"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792549","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792549","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792549","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014219634","display_name":"Hangyu Ye","orcid":"https://orcid.org/0000-0001-9433-8261"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangyu Ye","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9433-8261","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018175815","display_name":"Liyao Xiang","orcid":"https://orcid.org/0000-0003-0165-4930"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyao Xiang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China and Shanghai Innovation Institute, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0165-4930","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China and Shanghai Innovation Institute, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133239121","display_name":"Naixuan Huang","orcid":"https://orcid.org/0009-0008-2661-9043"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Naixuan Huang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-2661-9043","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133278471","display_name":"Dongyue Yu","orcid":"https://orcid.org/0009-0006-8707-5911"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongyue Yu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-8707-5911","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032278358","display_name":"Lijun Zhang","orcid":"https://orcid.org/0000-0002-5015-5495"},"institutions":[{"id":"https://openalex.org/I4210127487","display_name":"Vision Technology (United States)","ror":"https://ror.org/03gmxkp43","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127487"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lijun Zhang","raw_affiliation_strings":["E-surfing Vision Technology Co., Ltd, China Telecom, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5015-5495","affiliations":[{"raw_affiliation_string":"E-surfing Vision Technology Co., Ltd, China Telecom, Shanghai, China","institution_ids":["https://openalex.org/I4210127487"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133260948","display_name":"Gang Wang","orcid":"https://orcid.org/0009-0008-3531-0814"},"institutions":[{"id":"https://openalex.org/I4210127487","display_name":"Vision Technology (United States)","ror":"https://ror.org/03gmxkp43","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127487"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gang Wang","raw_affiliation_strings":["E-surfing Vision Technology Co., Ltd, China Telecom, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-3531-0814","affiliations":[{"raw_affiliation_string":"E-surfing Vision Technology Co., Ltd, China Telecom, Shanghai, China","institution_ids":["https://openalex.org/I4210127487"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3275","last_page":"3286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.19859999418258667,"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/T11644","display_name":"Spam and Phishing Detection","score":0.19859999418258667,"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/T10028","display_name":"Topic Modeling","score":0.14139999449253082,"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/T11800","display_name":"User Authentication and Security Systems","score":0.11029999703168869,"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/leakage","display_name":"Leakage (economics)","score":0.5425000190734863},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.33480000495910645},{"id":"https://openalex.org/keywords/information-leakage","display_name":"Information leakage","score":0.3312999904155731},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3012000024318695}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5857999920845032},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.5425000190734863},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4174000024795532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3391000032424927},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C2779201187","wikidata":"https://www.wikidata.org/wiki/Q2775060","display_name":"Information leakage","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792549","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792549","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792549","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792549","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2066266646","https://openalex.org/W2155071529","https://openalex.org/W2798621538","https://openalex.org/W2911484372","https://openalex.org/W2946325696","https://openalex.org/W2963825865","https://openalex.org/W3172340245","https://openalex.org/W4283172211","https://openalex.org/W4292793781","https://openalex.org/W4385570240","https://openalex.org/W4402671103","https://openalex.org/W4404534210","https://openalex.org/W4405182239","https://openalex.org/W4410632664"],"related_works":[],"abstract_inverted_index":{"A":[0],"vast":[1],"amount":[2],"of":[3,60,92,111,119,161],"user-generated":[4,34,78],"content":[5,35,79],"is":[6,64],"uploaded":[7],"on":[8,133,167],"social":[9],"media":[10],"everyday,":[11],"potentially":[12],"being":[13],"collected":[14],"as":[15],"training":[16],"data":[17],"for":[18,32,76],"large":[19],"language":[20,93],"models,":[21],"and":[22,62,80,128,135,147],"thus":[23],"poses":[24],"severe":[25],"threats":[26],"to":[27,38,100],"individual":[28],"privacy.":[29],"Existing":[30],"approaches":[31],"protecting":[33],"often":[36],"fail":[37],"detect":[39],"implicit":[40,123,145],"privacy":[41,83,104],"leaks":[42,61,146],"which":[43,87],"are":[44],"not":[45],"directly":[46],"given":[47],"but":[48,66],"could":[49],"be":[50],"inferred":[51],"from":[52],"the":[53,77,89,96,102,109,112,153],"contextual":[54,103],"text":[55,69,174],"(clues).":[56],"The":[57],"precise":[58,97],"detection":[59],"clues":[63],"difficult":[65],"critical":[67],"in":[68,143,150,172],"sanitization.":[70,175],"We":[71],"propose":[72],"a":[73,82,117],"graph-based":[74],"model":[75],"build":[81],"leakage":[84,105],"detector":[85],"PrivSniffer":[86,164],"integrates":[88],"inference":[90],"capability":[91,142],"models":[94],"with":[95],"graph":[98],"search,":[99],"capture":[101],"(CPL).":[106],"To":[107],"evaluate":[108],"effectiveness":[110],"framework,":[113],"we":[114],"create":[115],"SynthLeak,":[116,168],"dataset":[118],"dialogues":[120],"containing":[121],"human-labeled":[122],"leaks,":[124],"while":[125],"featuring":[126],"diversity":[127],"naturalness.":[129],"Our":[130],"experimental":[131],"results":[132],"SynthLeak":[134],"several":[136],"other":[137],"benchmarks":[138],"reveal":[139],"PrivSniffer's":[140],"superior":[141],"detecting":[144],"CPLs.":[148],"Particularly":[149],"CPL":[151],"detection,":[152],"state-of-the-art":[154],"approach":[155],"achieves":[156],"only":[157],"an":[158],"F1":[159],"Score":[160],"0.36,":[162],"whereas":[163],"attains":[165],"0.59":[166],"showing":[169],"great":[170],"promise":[171],"real-world":[173]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-10T00:00:00"}