{"id":"https://openalex.org/W4392425374","doi":"https://doi.org/10.48550/arxiv.2402.16893","title":"The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)","display_name":"The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)","publication_year":2024,"publication_date":"2024-02-23","ids":{"openalex":"https://openalex.org/W4392425374","doi":"https://doi.org/10.48550/arxiv.2402.16893"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2402.16893","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.16893","pdf_url":"https://arxiv.org/pdf/2402.16893","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.16893","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081817176","display_name":"Shenglai Zeng","orcid":"https://orcid.org/0009-0001-9664-8017","observed_orcids":["https://orcid.org/0009-0001-9664-8017"]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeng, Shenglai","raw_affiliation_strings":["Michigan State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086844015","display_name":"Jiankun Zhang","orcid":"https://orcid.org/0000-0001-7832-5268","observed_orcids":["https://orcid.org/0000-0001-7832-5268"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiankun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108946895","display_name":"Pengfei He","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"He, Pengfei","raw_affiliation_strings":["Michigan State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xing, Yue","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xing, Yue","raw_affiliation_strings":["Michigan State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101677601","display_name":"Yiding Liu","orcid":"https://orcid.org/0000-0001-6857-261X","observed_orcids":["https://orcid.org/0000-0001-6857-261X"]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Yiding","raw_affiliation_strings":["Baidu , Inc "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu , Inc ","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102012660","display_name":"Xu Han","orcid":"https://orcid.org/0000-0003-3707-660X","observed_orcids":["https://orcid.org/0000-0003-3707-660X","https://orcid.org/0000-0003-4417-9340"]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu, Han","raw_affiliation_strings":["Michigan State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101744064","display_name":"Jie Ren","orcid":"https://orcid.org/0000-0001-9398-8764","observed_orcids":["https://orcid.org/0000-0001-9398-8764"]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ren, Jie","raw_affiliation_strings":["Michigan State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050255638","display_name":"Shuaiqiang Wang","orcid":"https://orcid.org/0000-0002-9212-1947","observed_orcids":["https://orcid.org/0000-0002-9212-1947"]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Shuaiqiang","raw_affiliation_strings":["Baidu , Inc "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu , Inc ","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yin, Dawei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin, Dawei","raw_affiliation_strings":["Baidu , Inc "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu , Inc ","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chang, Yi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5040639891","display_name":"Jiliang Tang","orcid":"https://orcid.org/0000-0001-7125-3898","observed_orcids":["https://orcid.org/0000-0001-7125-3898"]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tang, Jiliang","raw_affiliation_strings":["Michigan State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]}],"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":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.7211999893188477,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.7211999893188477,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.2538999915122986,"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/T10028","display_name":"Topic Modeling","score":0.008700000122189522,"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/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":1.0},{"id":"https://openalex.org/keywords/data-privacy","display_name":"data privacy","score":0.9369999766349792},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8209999799728394},{"id":"https://openalex.org/keywords/training-data-leakage","display_name":"training data leakage","score":0.7760000228881836},{"id":"https://openalex.org/keywords/privacy-attacks","display_name":"privacy attacks","score":0.8859999775886536},{"id":"https://openalex.org/keywords/privacy-protection","display_name":"privacy preservation","score":0.781000018119812}],"concepts":[{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.6056810617446899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43727853894233704},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3446745276451111}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2402.16893","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.16893","pdf_url":"https://arxiv.org/pdf/2402.16893","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2402.16893","doi":"https://doi.org/10.48550/arxiv.2402.16893","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.16893","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.16893","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.16893","pdf_url":"https://arxiv.org/pdf/2402.16893","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392425374.pdf","grobid_xml":"https://content.openalex.org/works/W4392425374.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7119472059","https://openalex.org/W4408354281","https://openalex.org/W7160380836","https://openalex.org/W7222852277","https://openalex.org/W6979275415","https://openalex.org/W4408977202","https://openalex.org/W7165900875","https://openalex.org/W4405173318","https://openalex.org/W7169610995","https://openalex.org/W7213420957"],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"is":[3,19,130],"a":[4,20],"powerful":[5],"technique":[6,38],"to":[7],"facilitate":[8],"language":[9,33],"model":[10],"with":[11,64],"proprietary":[12],"and":[13,124],"private":[14,78],"data,":[15,91],"where":[16],"data":[17],"privacy":[18,29,50,115],"pivotal":[21],"concern.":[22],"Whereas":[23],"extensive":[24,61],"research":[25],"has":[26],"demonstrated":[27],"the":[28,36,42,70,77,82,89,99,102],"risks":[30],"of":[31,45,72,101,117],"large":[32],"models":[34],"(LLMs),":[35],"RAG":[37,73,87,96,125],"could":[39],"potentially":[40],"reshape":[41],"inherent":[43],"behaviors":[44],"LLM":[46],"generation,":[47],"posing":[48],"new":[49,83,109],"issues":[51],"that":[52,95],"are":[53],"currently":[54],"under-explored.":[55],"In":[56],"this":[57,112],"work,":[58],"we":[59,92,107],"conduct":[60],"empirical":[62],"studies":[63],"novel":[65],"attack":[66],"methods,":[67],"which":[68,120],"demonstrate":[69],"vulnerability":[71],"systems":[74,126],"on":[75,88],"leaking":[76],"retrieval":[79,90],"database.":[80],"Despite":[81],"risk":[84],"brought":[85],"by":[86],"further":[93],"reveal":[94],"can":[97],"mitigate":[98],"leakage":[100],"LLMs'":[103],"training":[104],"data.":[105],"Overall,":[106],"provide":[108],"insights":[110],"in":[111],"paper":[113],"for":[114],"protection":[116],"retrieval-augmented":[118],"LLMs,":[119],"benefit":[121],"both":[122],"LLMs":[123],"builders.":[127],"Our":[128],"code":[129],"available":[131],"at":[132],"https://github.com/phycholosogy/RAG-privacy.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2024-03-05T00:00:00"}
