{"id":"https://openalex.org/W4415222863","doi":"https://doi.org/10.1145/3730567.3732912","title":"An In-Depth Investigation of Data Collection in LLM App Ecosystems","display_name":"An In-Depth Investigation of Data Collection in LLM App Ecosystems","publication_year":2025,"publication_date":"2025-10-15","ids":{"openalex":"https://openalex.org/W4415222863","doi":"https://doi.org/10.1145/3730567.3732912"},"language":"en","primary_location":{"id":"doi:10.1145/3730567.3732912","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3730567.3732912","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3730567.3732912","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 2025 ACM Internet Measurement Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3730567.3732912","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100731116","display_name":"Yuhao Wu","orcid":"https://orcid.org/0000-0001-9155-3484"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuhao Wu","raw_affiliation_strings":["Washington University in St. Louis, St. Louis, MO, USA"],"raw_orcid":"https://orcid.org/0000-0001-9155-3484","affiliations":[{"raw_affiliation_string":"Washington University in St. Louis, St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107454137","display_name":"Evin Jaff","orcid":null},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evin Jaff","raw_affiliation_strings":["Washington University in St. Louis, St. Louis, MO, USA"],"raw_orcid":"https://orcid.org/0009-0002-3489-0040","affiliations":[{"raw_affiliation_string":"Washington University in St. Louis, St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100575521","display_name":"Ke Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Yang","raw_affiliation_strings":["Washington University in St. Louis, St. Louis, MO, USA"],"raw_orcid":"https://orcid.org/0009-0008-0375-7283","affiliations":[{"raw_affiliation_string":"Washington University in St. Louis, St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404897","display_name":"Ning Zhang","orcid":"https://orcid.org/0000-0003-0670-2161"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ning Zhang","raw_affiliation_strings":["Washington University in St. Louis, St. Louis, MO, USA"],"raw_orcid":"https://orcid.org/0000-0003-0670-2161","affiliations":[{"raw_affiliation_string":"Washington University in St. Louis, St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074510752","display_name":"Umar Iqbal","orcid":"https://orcid.org/0000-0003-1416-4113"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umar Iqbal","raw_affiliation_strings":["Washington University in St. Louis, St. Louis, MO, USA"],"raw_orcid":"https://orcid.org/0000-0003-1416-4113","affiliations":[{"raw_affiliation_string":"Washington University in St. Louis, St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204465549"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"150","last_page":"170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9926999807357788,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9926999807357788,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9907000064849854,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.7972999811172485},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.7400000095367432},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.593999981880188},{"id":"https://openalex.org/keywords/enforcement","display_name":"Enforcement","score":0.5601000189781189},{"id":"https://openalex.org/keywords/data-sharing","display_name":"Data sharing","score":0.5169000029563904},{"id":"https://openalex.org/keywords/privacy-policy","display_name":"Privacy policy","score":0.44429999589920044},{"id":"https://openalex.org/keywords/open-data","display_name":"Open data","score":0.4438000023365021},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.41929998993873596},{"id":"https://openalex.org/keywords/mobile-apps","display_name":"Mobile apps","score":0.37059998512268066}],"concepts":[{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.7972999811172485},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.7400000095367432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6319000124931335},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.593999981880188},{"id":"https://openalex.org/C2779777834","wikidata":"https://www.wikidata.org/wiki/Q4202277","display_name":"Enforcement","level":2,"score":0.5601000189781189},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.5371999740600586},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.5169000029563904},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4453999996185303},{"id":"https://openalex.org/C102938260","wikidata":"https://www.wikidata.org/wiki/Q1999831","display_name":"Privacy policy","level":3,"score":0.44429999589920044},{"id":"https://openalex.org/C2780535194","wikidata":"https://www.wikidata.org/wiki/Q309901","display_name":"Open data","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.390500009059906},{"id":"https://openalex.org/C2988145974","wikidata":"https://www.wikidata.org/wiki/Q620615","display_name":"Mobile apps","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.29190000891685486},{"id":"https://openalex.org/C197352329","wikidata":"https://www.wikidata.org/wiki/Q1093434","display_name":"Citizen science","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C49895821","wikidata":"https://www.wikidata.org/wiki/Q5227368","display_name":"Data verification","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C2780262971","wikidata":"https://www.wikidata.org/wiki/Q44554","display_name":"Law enforcement","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C69360830","wikidata":"https://www.wikidata.org/wiki/Q1172237","display_name":"Data Protection Act 1998","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2669000029563904},{"id":"https://openalex.org/C2777516300","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data discovery","level":3,"score":0.2653999924659729},{"id":"https://openalex.org/C2780866740","wikidata":"https://www.wikidata.org/wiki/Q5227345","display_name":"Data retention","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C2779794324","wikidata":"https://www.wikidata.org/wiki/Q3814081","display_name":"App store","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3730567.3732912","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3730567.3732912","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3730567.3732912","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 2025 ACM Internet Measurement Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3730567.3732912","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3730567.3732912","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3730567.3732912","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 2025 ACM Internet Measurement Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4849776441","display_name":null,"funder_award_id":"N00014-24-1-2663","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4854600781","display_name":"Collaborative Research: SWIFT: Closing the Loop for Accountable Interference-free Spectrum Sharing with Passive Radio Receivers","funder_award_id":"2229427","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6820632708","display_name":"Collaborative Research: SaTC: CORE: Medium: A Networking Perspective of Blockchain Security: Modeling, Analysis, and Defense","funder_award_id":"2154930","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309650","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415222863.pdf","grobid_xml":"https://content.openalex.org/works/W4415222863.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2784134919","https://openalex.org/W2986967943","https://openalex.org/W3015767612","https://openalex.org/W3173777717","https://openalex.org/W4385679821"],"related_works":[],"abstract_inverted_index":{"LLM":[0,21,37,61],"app":[1,62,68],"(tool)":[2],"ecosystems":[3],"are":[4,23,179],"rapidly":[5],"evolving":[6],"to":[7,54,79,150],"support":[8],"sophisticated":[9],"use":[10],"cases":[11],"that":[12,20,99,122,169],"often":[13],"require":[14],"extensive":[15],"user":[16,40],"data":[17,41,58,93,103,109,117,156,177,189],"collection.":[18],"Given":[19],"apps":[22,44],"developed":[24],"by":[25,36,128,139,158],"third":[26],"parties":[27],"and":[28,90,107],"anecdotal":[29],"evidence":[30],"indicating":[31],"inconsistent":[32],"enforcement":[33],"of":[34,60,85,155,174,184],"policies":[35,127],"platforms,":[38],"sharing":[39],"with":[42,111,160,181],"these":[43],"presents":[45],"significant":[46],"privacy":[47,146,164],"risks.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,142],"aim":[53],"bring":[55],"transparency":[56],"in":[57,162],"practices":[59],"ecosystems.":[63],"We":[64,74,120],"examine":[65],"OpenAI's":[66,126],"GPT":[67,86],"ecosystem":[69],"as":[70,133],"a":[71],"case":[72],"study.":[73],"propose":[75],"an":[76,144],"LLM-based":[77,145],"framework":[78,149],"analyze":[80],"the":[81,153,170,175],"natural":[82],"language":[83],"specifications":[84],"Actions":[87,100,113,124,159,185],"(custom":[88],"tools)":[89],"assess":[91],"their":[92,163,188],"collection":[94,157,190],"practices.":[95,191],"Our":[96,166],"analysis":[97,148],"reveals":[98],"collect":[101],"excessive":[102],"across":[104],"24":[105],"categories":[106],"145":[108],"types,":[110],"third-party":[112],"collecting":[114,129],"6.03%":[115],"more":[116],"on":[118],"average.":[119],"find":[121],"several":[123],"violate":[125],"sensitive":[130],"information,":[131],"such":[132],"passwords,":[134],"which":[135],"is":[136],"explicitly":[137],"prohibited":[138],"OpenAI.":[140],"Lastly,":[141],"develop":[143],"policy":[147],"automatically":[151],"check":[152],"consistency":[154],"disclosures":[161,171],"policies.":[165],"measurements":[167],"indicate":[168],"for":[172],"most":[173],"collected":[176],"types":[178],"omitted,":[180],"only":[182],"5.8%":[183],"clearly":[186],"disclosing":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-16T00:00:00"}