{"id":"https://openalex.org/W4412377840","doi":"https://doi.org/10.1145/3726302.3730110","title":"Unsupervised Corpus Poisoning Attacks in Continuous Space for Dense Retrieval","display_name":"Unsupervised Corpus Poisoning Attacks in Continuous Space for Dense Retrieval","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412377840","doi":"https://doi.org/10.1145/3726302.3730110"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730110","doi":"https://doi.org/10.1145/3726302.3730110","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730110","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730110","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730110","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100727698","display_name":"Yongkang Li","orcid":"https://orcid.org/0000-0001-6837-6184","observed_orcids":["https://orcid.org/0000-0001-6837-6184"]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yongkang Li","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-6837-6184","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041404983","display_name":"Panagiotis Eustratiadis","orcid":"https://orcid.org/0000-0002-9407-1293","observed_orcids":["https://orcid.org/0000-0002-9407-1293"]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Panagiotis Eustratiadis","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-9407-1293","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034714310","display_name":"Simon Lupart","orcid":"https://orcid.org/0009-0008-2383-4557","observed_orcids":["https://orcid.org/0009-0008-2383-4557"]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Simon Lupart","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0009-0008-2383-4557","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055639036","display_name":"Evangelos Kanoulas","orcid":"https://orcid.org/0000-0002-8312-0694","observed_orcids":["https://orcid.org/0000-0002-8312-0694"]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Evangelos Kanoulas","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-8312-0694","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":3.0165,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91271769,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2452","last_page":"2462"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994999766349792,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994999766349792,"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":9.999999747378752e-05,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0,"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/dense-retrieval","display_name":"dense retrieval","score":0.859000027179718},{"id":"https://openalex.org/keywords/adversarial-examples","display_name":"adversarial examples","score":0.8500000238418579},{"id":"https://openalex.org/keywords/black-box-attacks","display_name":"black-box attacks","score":0.6610000133514404},{"id":"https://openalex.org/keywords/white-box-attacks","display_name":"white-box attacks","score":0.9020000100135803},{"id":"https://openalex.org/keywords/adversarial-text-generation","display_name":"adversarial text generation","score":0.7170000076293945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7352467775344849},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5563626289367676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5375672578811646},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3966335952281952},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3726302.3730110","doi":"https://doi.org/10.1145/3726302.3730110","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730110","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730110","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire/ed341b68-e08a-496f-84a9-d3e71e29ca0c","doi":null,"is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/unsupervised-corpus-poisoning-attacks-in-continuous-space-for-dense-retrieval(ed341b68-e08a-496f-84a9-d3e71e29ca0c).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arXiv.org:2504.17884","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.17884","pdf_url":"https://arxiv.org/pdf/2504.17884","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.17884","doi":"https://doi.org/10.48550/arxiv.2504.17884","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.17884","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730110","doi":"https://doi.org/10.1145/3726302.3730110","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730110","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730110","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4096073789","display_name":null,"funder_award_id":"202308440220","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G5372375302","display_name":"Personality And Conversational INformatiOn Access (PACINO)","funder_award_id":"215742","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G5665784013","display_name":null,"funder_award_id":"202308440220","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G6280615682","display_name":"Low Resource Chat-based Conversational Intelligence","funder_award_id":"NWA.1389.20.183","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412377840.pdf","grobid_xml":"https://content.openalex.org/works/W4412377840.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2798658104","https://openalex.org/W2799194071","https://openalex.org/W2912924812","https://openalex.org/W2950491307","https://openalex.org/W3015883388","https://openalex.org/W3101033885","https://openalex.org/W3101449015","https://openalex.org/W3103801215","https://openalex.org/W3153015371","https://openalex.org/W3217305727","https://openalex.org/W4224330422","https://openalex.org/W4229078373","https://openalex.org/W4297834088","https://openalex.org/W4308644260","https://openalex.org/W4310923309","https://openalex.org/W4327644550","https://openalex.org/W4327810158","https://openalex.org/W4384652171","https://openalex.org/W4385571232","https://openalex.org/W4385571692","https://openalex.org/W4385571915","https://openalex.org/W4385572432","https://openalex.org/W4385572770","https://openalex.org/W4385573354","https://openalex.org/W4387846590","https://openalex.org/W4389519591","https://openalex.org/W4389520055","https://openalex.org/W4389520346","https://openalex.org/W4400526199","https://openalex.org/W4400527475","https://openalex.org/W4401306886","https://openalex.org/W4401381293","https://openalex.org/W4405143982","https://openalex.org/W4409166617","https://openalex.org/W4412888701"],"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/W3204019825"],"abstract_inverted_index":{"This":[0],"paper":[1],"concerns":[2],"corpus":[3,161,187],"poisoning":[4,188],"attacks":[5,43,191],"in":[6,39,53,62,74,207,225],"dense":[7],"information":[8],"retrieval,":[9],"where":[10,143],"an":[11,69,159],"adversary":[12,124,145],"attempts":[13],"to":[14,117,218,242,257],"compromise":[15],"the":[16,33,40,54,63,75,85,89,93,102,106,123,129,141,144,151,219,226,229,245],"ranking":[17],"performance":[18],"of":[19,28,87,140,247],"a":[20,25,81,119,136,182,186,194,197],"search":[21,50],"algorithm":[22],"by":[23],"injecting":[24],"small":[26],"number":[27],"maliciously":[29],"generated":[30],"documents":[31],"into":[32],"corpus.Our":[34],"work":[35,116],"addresses":[36],"two":[37,179,209],"limitations":[38],"current":[41],"literature.First,":[42],"that":[44,72,122,163,238],"perform":[45],"adversarial":[46,96,109,160,205,233],"gradient-based":[47],"word":[48,222],"substitution":[49,223],"do":[51],"so":[52],"discrete":[55],"lexical":[56],"space,":[57],"while":[58,99],"retrieval":[59],"itself":[60],"happens":[61],"continuous":[64],"embedding":[65,76],"space.We":[66],"thus":[67],"propose":[68],"optimization":[70],"method":[71,201,235],"operates":[73],"space":[77],"directly.Specifically,":[78],"we":[79,133],"train":[80],"perturbation":[82],"model":[83],"with":[84,228],"objective":[86],"maintaining":[88],"geometric":[90],"distance":[91],"between":[92,105],"original":[94,107],"and":[95,108,166,185,196,252],"document":[97],"embeddings,":[98],"also":[100],"maximizing":[101],"token-level":[103],"dissimilarity":[104],"documents.Second,":[110],"it":[111],"is":[112,158,164,239,253],"common":[113],"for":[114],"related":[115,180],"have":[118],"strong":[120],"assumption":[121],"has":[125],"prior":[126,148],"knowledge":[127,149],"about":[128,150],"queries.In":[130],"this":[131],"paper,":[132],"focus":[134],"on":[135,172,178],"more":[137,240,255],"challenging":[138],"variant":[139],"problem":[142],"assumes":[146],"no":[147],"query":[152],"distribution":[153,246],"(hence,":[154],"unsupervised).Our":[155],"core":[156],"contribution":[157],"attack":[162,184],"fast":[165],"effective.We":[167],"present":[168],"comprehensive":[169],"experimental":[170],"results":[171],"both":[173,193],"in-and":[174],"out-of-domain":[175],"datasets,":[176],"focusing":[177],"tasks:":[181],"top-1":[183],"attack.We":[189],"consider":[190],"under":[192,208,244],"white-box":[195],"black-box":[198],"setting.Notably,":[199],"our":[200,232],"can":[202],"generate":[203],"successful":[204],"examples":[206],"minutes":[210],"per":[211],"target":[212],"document;":[213],"four":[214],"times":[215],"faster":[216],"compared":[217],"fastest":[220],"gradientbased":[221],"methods":[224],"literature":[227],"same":[230],"hardware.Furthermore,":[231],"generation":[234],"generates":[236],"text":[237,249],"likely":[241],"occur":[243],"natural":[248],"(low":[250],"perplexity),":[251],"therefore":[254],"difficult":[256],"detect.":[258]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}