{"id":"https://openalex.org/W7123336521","doi":"https://doi.org/10.1109/tetc.2025.3648749","title":"MatcHEd: Privacy-Preserving Set Similarity Based on MinHash","display_name":"MatcHEd: Privacy-Preserving Set Similarity Based on MinHash","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123336521","doi":"https://doi.org/10.1109/tetc.2025.3648749"},"language":null,"primary_location":{"id":"doi:10.1109/tetc.2025.3648749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2025.3648749","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computing","raw_type":"journal-article"},"type":"article","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/A5111888969","display_name":"R. Shokri","orcid":"https://orcid.org/0009-0006-5576-3808"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rostin Shokri","raw_affiliation_strings":["Electrical &#x0026; Computer Engineering Department, University of Delaware, Newark, DE, USA"],"raw_orcid":"https://orcid.org/0009-0007-8160-5667","affiliations":[{"raw_affiliation_string":"Electrical &#x0026; Computer Engineering Department, University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011327501","display_name":"Charles Gouert","orcid":"https://orcid.org/0000-0002-7670-830X"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Gouert","raw_affiliation_strings":["Electrical &#x0026; Computer Engineering Department, University of Delaware, Newark, DE, USA"],"raw_orcid":"https://orcid.org/0000-0002-7670-830X","affiliations":[{"raw_affiliation_string":"Electrical &#x0026; Computer Engineering Department, University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064496184","display_name":"Nektarios Georgios Tsoutsos","orcid":"https://orcid.org/0000-0002-5769-0124"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nektarios Georgios Tsoutsos","raw_affiliation_strings":["Electrical &#x0026; Computer Engineering Department, University of Delaware, Newark, DE, USA"],"raw_orcid":"https://orcid.org/0000-0002-5769-0124","affiliations":[{"raw_affiliation_string":"Electrical &#x0026; Computer Engineering Department, University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111888969"],"corresponding_institution_ids":["https://openalex.org/I86501945"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07228624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":"1","first_page":"146","last_page":"159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10237","display_name":"Cryptography and Data Security","score":0.8608999848365784,"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/T10237","display_name":"Cryptography and Data Security","score":0.8608999848365784,"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":0.08720000088214874,"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/T11719","display_name":"Data Quality and Management","score":0.011500000022351742,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/encryption","display_name":"Encryption","score":0.7177000045776367},{"id":"https://openalex.org/keywords/bitwise-operation","display_name":"Bitwise operation","score":0.5863999724388123},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5648000240325928},{"id":"https://openalex.org/keywords/homomorphic-encryption","display_name":"Homomorphic encryption","score":0.5508000254631042},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.49549999833106995},{"id":"https://openalex.org/keywords/cryptography","display_name":"Cryptography","score":0.40869998931884766},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4020000100135803},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3894999921321869},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3734999895095825},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.366100013256073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7946000099182129},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.7177000045776367},{"id":"https://openalex.org/C134765980","wikidata":"https://www.wikidata.org/wiki/Q879126","display_name":"Bitwise operation","level":2,"score":0.5863999724388123},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5648000240325928},{"id":"https://openalex.org/C158338273","wikidata":"https://www.wikidata.org/wiki/Q2154943","display_name":"Homomorphic encryption","level":3,"score":0.5508000254631042},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.49549999833106995},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.492000013589859},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4246000051498413},{"id":"https://openalex.org/C178489894","wikidata":"https://www.wikidata.org/wiki/Q8789","display_name":"Cryptography","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C93974786","wikidata":"https://www.wikidata.org/wiki/Q1589480","display_name":"Ciphertext","level":3,"score":0.301800012588501},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29649999737739563},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.29499998688697815},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C11045955","wikidata":"https://www.wikidata.org/wiki/Q1162410","display_name":"ElGamal encryption","level":4,"score":0.2743000090122223},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C187455244","wikidata":"https://www.wikidata.org/wiki/Q942353","display_name":"Boolean function","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C81539297","wikidata":"https://www.wikidata.org/wiki/Q33456","display_name":"Exponentiation","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C113138325","wikidata":"https://www.wikidata.org/wiki/Q864457","display_name":"Knapsack problem","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetc.2025.3648749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2025.3648749","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6841259598731995,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W913176383","https://openalex.org/W1798609567","https://openalex.org/W1990339094","https://openalex.org/W1991800036","https://openalex.org/W1992291252","https://openalex.org/W2001759130","https://openalex.org/W2007466965","https://openalex.org/W2010126199","https://openalex.org/W2012833704","https://openalex.org/W2031533839","https://openalex.org/W2059444062","https://openalex.org/W2061980234","https://openalex.org/W2080747411","https://openalex.org/W2084462505","https://openalex.org/W2098290658","https://openalex.org/W2132069633","https://openalex.org/W2148885851","https://openalex.org/W2157116240","https://openalex.org/W2169660454","https://openalex.org/W2177209050","https://openalex.org/W2222068751","https://openalex.org/W2554750353","https://openalex.org/W2585287165","https://openalex.org/W2751501713","https://openalex.org/W2766393794","https://openalex.org/W2768174108","https://openalex.org/W2792498333","https://openalex.org/W2893494605","https://openalex.org/W2911038074","https://openalex.org/W2950150251","https://openalex.org/W2976620030","https://openalex.org/W2986900277","https://openalex.org/W3015685940","https://openalex.org/W3027260415","https://openalex.org/W3120341667","https://openalex.org/W3157813311","https://openalex.org/W4312566136","https://openalex.org/W4376626897","https://openalex.org/W4389539753","https://openalex.org/W4407783215"],"related_works":[],"abstract_inverted_index":{"Fully":[0],"homomorphic":[1],"encryption":[2],"(FHE)":[3],"enables":[4],"arbitrary":[5],"computation":[6,229],"on":[7,230],"encrypted":[8,18,27,53,132,169,228,247],"data,":[9],"but":[10],"certain":[11],"applications":[12],"remain":[13],"prohibitively":[14],"expensive":[15,34,76],"in":[16,23,68,122,145],"the":[17,37,58,62,81,85,100,119,123,131,137,164,178,204,211,217],"domain.":[19],"As":[20],"a":[21,49,107,114,172,242],"case":[22],"point,":[24],"comparing":[25],"two":[26,90],"sets":[28,91],"of":[29,40,92,102,166,206,214],"data":[30],"is":[31,87,222],"extremely":[32],"computationally":[33],"due":[35],"to":[36,88,135,161,195,210],"large":[38,142],"number":[39,101,205],"comparison":[41],"operators":[42],"required.":[43],"In":[44,171],"this":[45],"work,":[46],"we":[47,152],"propose":[48],"novel":[50],"methodology":[51],"for":[52,190,226],"set":[54],"similarity":[55,219],"inspired":[56],"by":[57,105,240],"MinHash":[59,95],"algorithm":[60,96],"and":[61,72,143,221,232],"CGGI":[63],"FHE":[64,69,147,174],"scheme.":[65],"Doing":[66],"comparisons":[67,103,207],"requires":[70],"comparators":[71],"multiplexers":[73],"or":[74],"an":[75,146,154],"approximation,":[77],"which":[78,188],"further":[79],"increases":[80],"latency,":[82],"especially":[83],"when":[84],"goal":[86],"compare":[89],"data.":[93],"The":[94],"can":[97,181],"significantly":[98],"reduce":[99],"required":[104,134,208],"employing":[106],"special":[108],"Carter-Wegman":[109,197],"(CW)":[110],"hash":[111,125],"function":[112,159],"as":[113,163],"key":[115,128],"building":[116],"block.":[117],"However,":[118],"modulus":[120],"operation":[121],"CW":[124],"becomes":[126],"another":[127],"bottleneck":[129],"because":[130],"sub-circuits":[133],"perform":[136],"modular":[138],"reduction":[139],"are":[140],"very":[141],"inefficient":[144],"setting.":[148],"Towards":[149],"that":[150],"end,":[151],"introduce":[153],"efficient":[155,227],"bitwise":[156,179],"FHE-friendly":[157],"digest":[158],"(FFD)":[160],"employ":[162],"cornerstone":[165],"our":[167,200,238],"proposed":[168],"set-similarity.":[170],"Boolean":[173,186],"scheme":[175],"like":[176],"CGGI,":[177],"operations":[180],"be":[182],"implemented":[183],"efficiently":[184],"with":[185],"gates,":[187],"allows":[189],"faster":[191],"evaluation":[192],"times":[193],"relative":[194,209],"standard":[196],"constructions.":[198],"Overall,":[199],"approach":[201,213,239],"drastically":[202],"reduces":[203],"baseline":[212],"directly":[215],"computing":[216],"Jaccard":[218],"coefficients,":[220],"inherently":[223],"parallelizable,":[224],"allowing":[225],"multi-CPU":[231],"GPU-based":[233],"cloud":[234],"servers.":[235],"We":[236],"validate":[237],"performing":[241],"privacy-preserving":[243],"plagiarism":[244],"detection":[245],"across":[246],"documents.":[248]},"counts_by_year":[],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2026-01-14T00:00:00"}
