{"id":"https://openalex.org/W4385080314","doi":"https://doi.org/10.1109/sp46215.2023.10179334","title":"SNAP: Efficient Extraction of Private Properties with Poisoning","display_name":"SNAP: Efficient Extraction of Private Properties with Poisoning","publication_year":2023,"publication_date":"2023-05-01","ids":{"openalex":"https://openalex.org/W4385080314","doi":"https://doi.org/10.1109/sp46215.2023.10179334"},"language":"en","primary_location":{"id":"doi:10.1109/sp46215.2023.10179334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sp46215.2023.10179334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Symposium on Security and Privacy (SP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045507972","display_name":"Harsh Chaudhari","orcid":"https://orcid.org/0009-0000-3269-5685"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Harsh Chaudhari","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087805747","display_name":"John Abascal","orcid":null},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"John Abascal","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035574749","display_name":"Alina Oprea","orcid":"https://orcid.org/0000-0002-4979-5292"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Alina Oprea","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054655342","display_name":"Matthew Jagielski","orcid":"https://orcid.org/0000-0002-9749-0696"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Jagielski","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006851333","display_name":"Florian Tram\u00e8r","orcid":"https://orcid.org/0000-0001-8703-8762"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Florian Tram\u00e8r","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034669615","display_name":"Jonathan Ullman","orcid":"https://orcid.org/0000-0002-0323-5564"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Jonathan Ullman","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"400","last_page":"417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9986000061035156,"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/T10237","display_name":"Cryptography and Data Security","score":0.9957000017166138,"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/extraction","display_name":"Extraction (chemistry)","score":0.6253770589828491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5450050234794617},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.17019882798194885},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.1214551329612732}],"concepts":[{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.6253770589828491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5450050234794617},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.17019882798194885},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.1214551329612732}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sp46215.2023.10179334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sp46215.2023.10179334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Symposium on Security and Privacy (SP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1552056088","https://openalex.org/W1583837637","https://openalex.org/W1834627138","https://openalex.org/W1873763122","https://openalex.org/W2040228409","https://openalex.org/W2110868467","https://openalex.org/W2535690855","https://openalex.org/W2612690371","https://openalex.org/W2752929869","https://openalex.org/W2774423163","https://openalex.org/W2795435272","https://openalex.org/W2897830718","https://openalex.org/W2942091739","https://openalex.org/W2962763344","https://openalex.org/W2962835266","https://openalex.org/W2963456518","https://openalex.org/W2965721472","https://openalex.org/W3035168593","https://openalex.org/W3096692244","https://openalex.org/W3120740533","https://openalex.org/W3122816307","https://openalex.org/W3150395569","https://openalex.org/W3154109599","https://openalex.org/W3200345107","https://openalex.org/W3213807399","https://openalex.org/W3214399478","https://openalex.org/W4286961857","https://openalex.org/W4288057780","https://openalex.org/W4308410483","https://openalex.org/W4308643663","https://openalex.org/W4385412495","https://openalex.org/W6631190155","https://openalex.org/W6676935882","https://openalex.org/W6684559340","https://openalex.org/W6686674283","https://openalex.org/W6735632633","https://openalex.org/W6739088070","https://openalex.org/W6746897123","https://openalex.org/W6749794497","https://openalex.org/W6763077247","https://openalex.org/W6763393573","https://openalex.org/W6775482175","https://openalex.org/W6779987556","https://openalex.org/W6781511523","https://openalex.org/W6782718173","https://openalex.org/W6787335730","https://openalex.org/W6795938332","https://openalex.org/W6796900644","https://openalex.org/W6801929890","https://openalex.org/W6801935883","https://openalex.org/W6803928340","https://openalex.org/W6810206781"],"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/W4396696052"],"abstract_inverted_index":{"Property":[0],"inference":[1,40,79,114,133],"attacks":[2,20,41,80],"allow":[3],"an":[4,111],"adversary":[5],"to":[6,30,163],"extract":[7],"global":[8],"properties":[9,192],"of":[10,62,77,89,104,126,180,183,193],"the":[11,56,75,83,90,95,129,143,177],"training":[12,58,91,174],"dataset":[13,92],"from":[14,196],"a":[15,59,67,87,166,181],"machine":[16,32],"learning":[17,33],"model.":[18,98],"Such":[19],"have":[21,46],"privacy":[22],"implications":[23],"for":[24,38],"data":[25],"owners":[26],"sharing":[27],"their":[28],"datasets":[29,198],"train":[31],"models.":[34],"Several":[35],"existing":[36],"approaches":[37],"property":[39,78,113,132,168,182],"against":[42],"deep":[43],"neural":[44],"networks":[45],"been":[47],"proposed":[48],"[1]":[49],"\u2013[3],":[50],"but":[51],"they":[52],"all":[53,172],"rely":[54],"on":[55,142,190],"attacker":[57,84],"large":[60,68],"number":[61],"shadow":[63],"models,":[64],"which":[65,82,117],"induces":[66],"computational":[69],"overhead.In":[70],"this":[71],"paper,":[72],"we":[73,109],"consider":[74],"setting":[76],"in":[81],"can":[85],"poison":[86],"subset":[88],"and":[93,122,175,199,203],"query":[94],"trained":[96],"target":[97],"Motivated":[99],"by":[100,135],"our":[101,161,188],"theoretical":[102],"analysis":[103],"model":[105],"confidences":[106],"under":[107],"poisoning,":[108],"design":[110],"efficient":[112],"attack,":[115],"SNAP,":[116],"obtains":[118],"higher":[119,149],"attack":[120,134,162,189],"success":[121,150],"requires":[123],"lower":[124],"amounts":[125],"poisoning":[127],"than":[128,152],"state-of-the-art":[130],"poisoning-based":[131],"Mahloujifar":[136],"et":[137],"al.":[138],"[3].":[139],"For":[140],"example,":[141],"Census":[144],"dataset,":[145],"SNAP":[146],"achieves":[147],"34%":[148],"rate":[151],"[3]":[153],"while":[154],"being":[155],"56.5\u00d7":[156],"faster.":[157],"We":[158,186],"also":[159],"extend":[160],"infer":[164],"whether":[165],"certain":[167],"was":[169],"present":[170],"at":[171],"during":[173],"estimate":[176],"exact":[178],"proportion":[179],"interest":[184],"efficiently.":[185],"evaluate":[187],"several":[191],"varying":[194],"proportions":[195],"four":[197],"demonstrate":[200],"SNAP\u2019s":[201],"generality":[202],"effectiveness.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}