{"id":"https://openalex.org/W2989576201","doi":"https://doi.org/10.1109/milcom52596.2021.9653027","title":"Privacy Leakage Avoidance with Switching Ensembles","display_name":"Privacy Leakage Avoidance with Switching Ensembles","publication_year":2021,"publication_date":"2021-11-29","ids":{"openalex":"https://openalex.org/W2989576201","doi":"https://doi.org/10.1109/milcom52596.2021.9653027","mag":"2989576201"},"language":"en","primary_location":{"id":"doi:10.1109/milcom52596.2021.9653027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/milcom52596.2021.9653027","pdf_url":null,"source":{"id":"https://openalex.org/S4363608138","display_name":"MILCOM 2021 - 2021 IEEE Military Communications Conference (MILCOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MILCOM 2021 - 2021 IEEE Military Communications Conference (MILCOM)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.07921","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078482977","display_name":"Rauf Izmailov","orcid":"https://orcid.org/0000-0002-7326-669X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rauf Izmailov","raw_affiliation_strings":["Peraton Labs Inc., NJ, USA"],"affiliations":[{"raw_affiliation_string":"Peraton Labs Inc., NJ, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027156916","display_name":"Peter Lin","orcid":"https://orcid.org/0000-0002-7430-8804"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Lin","raw_affiliation_strings":["Peraton Labs Inc., NJ, USA"],"affiliations":[{"raw_affiliation_string":"Peraton Labs Inc., NJ, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026999236","display_name":"Chris Mesterharm","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chris Mesterharm","raw_affiliation_strings":["Peraton Labs Inc., NJ, USA"],"affiliations":[{"raw_affiliation_string":"Peraton Labs Inc., NJ, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085795724","display_name":"Samyadeep Basu","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samyadeep Basu","raw_affiliation_strings":["University of Maryland, College Park, MD, USA","University of Maryland - College Park"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland - College Park","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078482977"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1269,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.29535163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"abs 1806 1246","issue":null,"first_page":"981","last_page":"986"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9958000183105469,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9739000201225281,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/inference","display_name":"Inference","score":0.8570694923400879},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7462615966796875},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6499506235122681},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6328407526016235},{"id":"https://openalex.org/keywords/information-leakage","display_name":"Information leakage","score":0.489952951669693},{"id":"https://openalex.org/keywords/leakage","display_name":"Leakage (economics)","score":0.48250889778137207},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4206051826477051},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3518676459789276},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.2613191604614258}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8570694923400879},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7462615966796875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6499506235122681},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6328407526016235},{"id":"https://openalex.org/C2779201187","wikidata":"https://www.wikidata.org/wiki/Q2775060","display_name":"Information leakage","level":2,"score":0.489952951669693},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.48250889778137207},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4206051826477051},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3518676459789276},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2613191604614258},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/milcom52596.2021.9653027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/milcom52596.2021.9653027","pdf_url":null,"source":{"id":"https://openalex.org/S4363608138","display_name":"MILCOM 2021 - 2021 IEEE Military Communications Conference (MILCOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MILCOM 2021 - 2021 IEEE Military Communications Conference (MILCOM)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1911.07921","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.07921","pdf_url":"https://arxiv.org/pdf/1911.07921","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"mag:2989576201","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1911.07921.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1911.07921","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.07921","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.07921","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.07921","pdf_url":"https://arxiv.org/pdf/1911.07921","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3267069314","display_name":null,"funder_award_id":"NM0476-19-C-0007","funder_id":"https://openalex.org/F4320332165","funder_display_name":"National Geospatial-Intelligence Agency"}],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320332165","display_name":"National Geospatial-Intelligence Agency","ror":"https://ror.org/02k4pxv54"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2989576201.pdf","grobid_xml":"https://content.openalex.org/works/W2989576201.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W9657784","https://openalex.org/W1473189865","https://openalex.org/W2027595342","https://openalex.org/W2051267297","https://openalex.org/W2099942492","https://openalex.org/W2144906988","https://openalex.org/W2151103935","https://openalex.org/W2161381512","https://openalex.org/W2180612164","https://openalex.org/W2243397390","https://openalex.org/W2335728318","https://openalex.org/W2408141691","https://openalex.org/W2460937040","https://openalex.org/W2461943168","https://openalex.org/W2512472178","https://openalex.org/W2532781556","https://openalex.org/W2535690855","https://openalex.org/W2535873859","https://openalex.org/W2593864460","https://openalex.org/W2603766943","https://openalex.org/W2617174679","https://openalex.org/W2807096445","https://openalex.org/W2884943453","https://openalex.org/W2902027132","https://openalex.org/W2954172636","https://openalex.org/W2962835266","https://openalex.org/W2964318098","https://openalex.org/W2979453344","https://openalex.org/W6657138077","https://openalex.org/W6703116779","https://openalex.org/W6728897251","https://openalex.org/W6734897383","https://openalex.org/W6738406820","https://openalex.org/W6752346538","https://openalex.org/W6756573353","https://openalex.org/W6764826176"],"related_works":["https://openalex.org/W3206966921","https://openalex.org/W2884943453","https://openalex.org/W3013068160","https://openalex.org/W3160121477","https://openalex.org/W3104406626","https://openalex.org/W2952270003","https://openalex.org/W3095101874","https://openalex.org/W3214437258","https://openalex.org/W3081595899","https://openalex.org/W3205533264","https://openalex.org/W3110459138","https://openalex.org/W3046102592","https://openalex.org/W2989885118","https://openalex.org/W3087067816","https://openalex.org/W3135646925","https://openalex.org/W3047064787","https://openalex.org/W3177170788","https://openalex.org/W3213807399","https://openalex.org/W2977787364","https://openalex.org/W2947134221"],"abstract_inverted_index":{"We":[0,82,180],"consider":[1],"membership":[2,99],"inference":[3,100,117],"attacks,":[4],"one":[5],"of":[6,63,71,87,120,149],"the":[7,37,41,59,72,126,130,142,145,187,188],"main":[8],"privacy":[9,56,88],"issues":[10],"in":[11,22,114,129,144,153],"machine":[12,43,74],"learning.":[13],"These":[14],"recently":[15],"developed":[16,52],"attacks":[17,101],"have":[18,50],"been":[19,51],"proven":[20],"successful":[21],"determining,":[23],"with":[24,91,105,186],"confidence":[25],"better":[26],"than":[27],"a":[28,32,84],"random":[29],"guess,":[30],"whether":[31],"given":[33],"sample":[34],"belongs":[35],"to":[36,53,167],"dataset":[38],"on":[39,193],"which":[40,95],"attacked":[42],"learning":[44,75],"model":[45],"was":[46],"trained.":[47],"Several":[48],"approaches":[49],"mitigate":[54],"this":[55],"leakage":[57,89],"but":[58],"tradeoff":[60],"performance":[61],"implications":[62],"these":[64],"defensive":[65],"mechanisms":[66],"(i.e.,":[67],"accuracy":[68,108],"and":[69,102,116,197],"utility":[70],"defended":[73],"model)":[76],"are":[77],"not":[78],"well":[79],"studied":[80],"yet.":[81],"propose":[83],"novel":[85],"approach":[86],"avoidance":[90],"switching":[92],"ensembles":[93],"(PASE),":[94],"protects":[96],"against":[97],"current":[98,131,189],"does":[103],"that":[104,150],"very":[106],"small":[107],"penalty,":[109],"while":[110],"requiring":[111],"acceptable":[112],"increase":[113],"training":[115,125,141,158,170],"time.":[118],"Instead":[119],"using":[121],"disjoint":[122],"subsets":[123,139],"for":[124,140,164,177],"classifiers":[127,143,166],"as":[128],"state-of-the-art":[132,190],"PATE":[133,191],"approach,":[134,192],"PASE":[135,183],"uses":[136],"significantly":[137,156],"overlapping":[138],"ensemble.":[146],"The":[147],"consequence":[148],"distinction":[151],"is":[152],"moving":[154],"from":[155],"reduced":[157,162,169,175],"sizes":[159,171],"(and,":[160,172],"correspondingly,":[161,173],"accuracy)":[163,176],"individual":[165,178],"insignificantly":[168,174],"classifiers.":[179],"test":[181],"our":[182],"method,":[184],"along":[185],"three":[194],"calibration":[195],"datasets":[196],"analyze":[198],"their":[199],"tradeoffs.":[200]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}