{"id":"https://openalex.org/W4385568142","doi":"https://doi.org/10.1145/3580305.3599297","title":"Deception by Omission: Using Adversarial Missingness to Poison Causal Structure Learning","display_name":"Deception by Omission: Using Adversarial Missingness to Poison Causal Structure Learning","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385568142","doi":"https://doi.org/10.1145/3580305.3599297"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599297","doi":"https://doi.org/10.1145/3580305.3599297","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599297","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599297","source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","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 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/10.1145/3580305.3599297","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045572599","display_name":"Deniz Koyuncu","orcid":"https://orcid.org/0000-0001-6316-8853","observed_orcids":["https://orcid.org/0000-0001-6316-8853"]},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deniz Koyuncu","raw_affiliation_strings":["Rensselaer Polytechnic Institute, Troy, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-6316-8853","affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038646656","display_name":"Alex Gittens","orcid":"https://orcid.org/0000-0003-3482-0157","observed_orcids":["https://orcid.org/0000-0003-3482-0157"]},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Gittens","raw_affiliation_strings":["Rensselaer Polytechnic Institute, Troy, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-3482-0157","affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073676361","display_name":"B\u00fclent Yener","orcid":"https://orcid.org/0000-0003-3989-6097","observed_orcids":["https://orcid.org/0000-0003-3989-6097"]},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"B\u00fclent Yener","raw_affiliation_strings":["Rensselaer Polytechnic Institute, Troy, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-3989-6097","affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030243906","display_name":"Moti M. Yung","orcid":"https://orcid.org/0000-0003-0848-0873","observed_orcids":["https://orcid.org/0000-0003-0848-0873"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Moti Yung","raw_affiliation_strings":["Google LLC & Columbia University, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-0848-0873","affiliations":[{"raw_affiliation_string":"Google LLC & Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07806249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":null,"first_page":"1164","last_page":"1175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9961000084877014,"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":0.9961000084877014,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.002199999988079071,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.00019999999494757503,"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-poisoning-attacks","display_name":"data poisoning","score":0.6809999942779541},{"id":"https://openalex.org/keywords/causal-discovery","display_name":"causal discovery","score":0.9829999804496765},{"id":"https://openalex.org/keywords/structural-causal-models","display_name":"structural causal models","score":0.7929999828338623},{"id":"https://openalex.org/keywords/adversarial-attacks","display_name":"adversarial attacks","score":0.5809999704360962},{"id":"https://openalex.org/keywords/observational-data","display_name":"observational data","score":0.6359999775886536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7301954030990601},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6999853253364563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6793112754821777},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.649238109588623},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6129288673400879},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.5241742134094238},{"id":"https://openalex.org/C2778403875","wikidata":"https://www.wikidata.org/wiki/Q20312394","display_name":"Adversarial machine learning","level":3,"score":0.5044182538986206},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.48500868678092957},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.47336336970329285},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.45748773217201233},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44234713912010193},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4100203812122345},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18203285336494446},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.14072000980377197},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10155653953552246},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3580305.3599297","doi":"https://doi.org/10.1145/3580305.3599297","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599297","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599297","source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","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 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2305.20043","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.20043","pdf_url":"https://arxiv.org/pdf/2305.20043","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.2305.20043","doi":"https://doi.org/10.48550/arxiv.2305.20043","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.20043","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":"doi:10.1145/3580305.3599297","doi":"https://doi.org/10.1145/3580305.3599297","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599297","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599297","source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","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 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385568142.pdf","grobid_xml":"https://content.openalex.org/works/W4385568142.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1785882633","https://openalex.org/W2073307618","https://openalex.org/W2077870633","https://openalex.org/W2115802951","https://openalex.org/W2132555912","https://openalex.org/W2134701672","https://openalex.org/W2807363941","https://openalex.org/W2875043134","https://openalex.org/W2952437217","https://openalex.org/W2973217491","https://openalex.org/W2997591727","https://openalex.org/W3012794253","https://openalex.org/W4212774754","https://openalex.org/W4248991387","https://openalex.org/W4290943920","https://openalex.org/W7133215752"],"related_works":["https://openalex.org/W4401933889","https://openalex.org/W7034286679","https://openalex.org/W2898990595","https://openalex.org/W2998855746","https://openalex.org/W3212918802","https://openalex.org/W4385562532","https://openalex.org/W2789929276","https://openalex.org/W4392182252","https://openalex.org/W4281726379","https://openalex.org/W4372260129"],"abstract_inverted_index":{"Causality-informed":[0],"machine":[1,17,36],"learning":[2,37,73,194],"has":[3,57],"been":[4],"proposed":[5],"as":[6],"an":[7],"avenue":[8],"for":[9,87,158],"achieving":[10],"many":[11],"of":[12,15,34,41,62,74,116,161,173,185],"the":[13,39,72,82,110,117,123,142,147,159,183],"goals":[14],"modern":[16],"learning,":[18],"from":[19,44],"ensuring":[20],"generalization":[21],"under":[22],"domain":[23],"shifts":[24],"to":[25,70,121,140,146],"attaining":[26],"fairness,":[27],"robustness,":[28],"and":[29,164,178],"interpretability.":[30],"A":[31],"key":[32],"component":[33],"causal":[35,42,76,125,192],"is":[38,91,100,169],"inference":[40],"structures":[43,126],"observational":[45],"data;":[46],"in":[47,127],"practice,":[48],"this":[49,97,137,150],"data":[50,66,83,120,180],"may":[51,67],"be":[52,68,85,141],"incompletely":[53],"observed.":[54],"Prior":[55],"work":[56,103],"demonstrated":[58],"that":[59],"adversarial":[60,98,186],"perturbations":[61],"completely":[63],"observed":[64],"training":[65,119],"used":[69],"force":[71],"inaccurate":[75],"structural":[77],"models":[78],"(SCMs).":[79],"However,":[80],"when":[81],"can":[84],"audited":[86],"correctness":[88],"(e.g.,":[89],"it":[90],"cryptographically":[92],"signed":[93,133],"by":[94],"its":[95],"source),":[96],"mechanism":[99],"invalidated.":[101],"This":[102],"introduces":[104],"a":[105,114,128,165],"novel":[106],"attack":[107,154],"methodology":[108],"wherein":[109],"adversary":[111],"deceptively":[112],"omits":[113],"portion":[115],"true":[118],"bias":[122],"learned":[124],"desired":[129],"manner":[130],"(under":[131],"strong":[132],"sample":[134],"input":[135],"validation,":[136],"behavior":[138],"seems":[139],"only":[143],"strategy":[144],"available":[145],"adversary).":[148],"Under":[149],"model,":[151],"theoretically":[152],"sound":[153],"mechanisms":[155],"are":[156],"derived":[157],"case":[160],"arbitrary":[162],"SCMs,":[163],"sample-efficient":[166],"learning-based":[167],"heuristic":[168],"given.":[170],"Experimental":[171],"validation":[172],"these":[174],"approaches":[175],"on":[176],"real":[177],"synthetic":[179],"sets":[181],"demonstrates":[182],"effectiveness":[184],"missingness":[187],"attacks":[188],"at":[189],"deceiving":[190],"popular":[191],"structure":[193],"algorithms.":[195]},"counts_by_year":[],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2023-08-05T00:00:00"}