{"id":"https://openalex.org/W3211574353","doi":"https://doi.org/10.1145/3460120.3484571","title":"Quantifying and Mitigating Privacy Risks of Contrastive Learning","display_name":"Quantifying and Mitigating Privacy Risks of Contrastive Learning","publication_year":2021,"publication_date":"2021-11-12","ids":{"openalex":"https://openalex.org/W3211574353","doi":"https://doi.org/10.1145/3460120.3484571","mag":"3211574353"},"language":"en","primary_location":{"id":"doi:10.1145/3460120.3484571","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460120.3484571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-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/A5074889369","display_name":"Xinlei He","orcid":"https://orcid.org/0000-0002-1526-6341"},"institutions":[{"id":"https://openalex.org/I4210128801","display_name":"Helmholtz Center for Information Security","ror":"https://ror.org/02njgxr09","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210128801"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Xinlei He","raw_affiliation_strings":["CISPA Helmholtz Center for Information Security, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"CISPA Helmholtz Center for Information Security, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210128801"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100354608","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0001-9229-7689"},"institutions":[{"id":"https://openalex.org/I4210128801","display_name":"Helmholtz Center for Information Security","ror":"https://ror.org/02njgxr09","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210128801"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["CISPA Helmholtz Center for Information Security, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"CISPA Helmholtz Center for Information Security, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210128801"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5074889369"],"corresponding_institution_ids":["https://openalex.org/I4210128801"],"apc_list":null,"apc_paid":null,"fwci":2.9913,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.92690097,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"845","last_page":"863"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9818000197410583,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9387000203132629,"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/computer-science","display_name":"Computer science","score":0.8265902996063232},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.767264187335968},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7140629291534424},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6814931035041809},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6726828813552856},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6091415882110596},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.43724191188812256},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4190223813056946},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1582781970500946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8265902996063232},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.767264187335968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7140629291534424},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6814931035041809},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6726828813552856},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6091415882110596},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.43724191188812256},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4190223813056946},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1582781970500946}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3460120.3484571","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460120.3484571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1966752340","display_name":null,"funder_award_id":"ZT-I-OO1 4","funder_id":"https://openalex.org/F4320325698","funder_display_name":"Helmholtz Association"}],"funders":[{"id":"https://openalex.org/F4320325698","display_name":"Helmholtz Association","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W9657784","https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W1882958252","https://openalex.org/W2117539524","https://openalex.org/W2118858186","https://openalex.org/W2180612164","https://openalex.org/W2461943168","https://openalex.org/W2516574342","https://openalex.org/W2535690855","https://openalex.org/W2592232824","https://openalex.org/W2593390416","https://openalex.org/W2617174679","https://openalex.org/W2617214882","https://openalex.org/W2620038827","https://openalex.org/W2757528734","https://openalex.org/W2787698406","https://openalex.org/W2789304371","https://openalex.org/W2794878842","https://openalex.org/W2795435272","https://openalex.org/W2796438033","https://openalex.org/W2798991696","https://openalex.org/W2799694080","https://openalex.org/W2807096445","https://openalex.org/W2884943453","https://openalex.org/W2887997457","https://openalex.org/W2888161220","https://openalex.org/W2889507104","https://openalex.org/W2898291644","https://openalex.org/W2905209730","https://openalex.org/W2906993533","https://openalex.org/W2926319231","https://openalex.org/W2930926105","https://openalex.org/W2945693042","https://openalex.org/W2946363484","https://openalex.org/W2947642149","https://openalex.org/W2956128647","https://openalex.org/W2976822050","https://openalex.org/W2981828710","https://openalex.org/W2987283559","https://openalex.org/W3005680577","https://openalex.org/W3010489274","https://openalex.org/W3013068160","https://openalex.org/W3014514837","https://openalex.org/W3027379683","https://openalex.org/W3033406728","https://openalex.org/W3038680626","https://openalex.org/W3046102592","https://openalex.org/W3071470454","https://openalex.org/W3088375704","https://openalex.org/W3103245149","https://openalex.org/W3103836116","https://openalex.org/W3104224589","https://openalex.org/W3106873467","https://openalex.org/W3112689365","https://openalex.org/W3120806613","https://openalex.org/W3126787694","https://openalex.org/W3127447688","https://openalex.org/W3173151551","https://openalex.org/W3177525997","https://openalex.org/W6638891565","https://openalex.org/W6687483927","https://openalex.org/W6691148622","https://openalex.org/W6740934225","https://openalex.org/W6747732332","https://openalex.org/W6776644305","https://openalex.org/W6781119697","https://openalex.org/W6781228435","https://openalex.org/W6784694379","https://openalex.org/W6804505112","https://openalex.org/W7043248672"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W4221142204"],"abstract_inverted_index":{"Data":[0],"is":[1,24,42,49,195,211],"the":[2,7,14,117,148,156,198,209,228],"key":[3],"factor":[4],"to":[5,29,50,84,95,110,178,185,190,197,206],"drive":[6],"development":[8],"of":[9,46,116,152,158,217],"machine":[10,105],"learning":[11,48,106,135,154,232],"(ML)":[12],"during":[13],"past":[15],"decade.":[16],"However,":[17,114],"high-quality":[18],"data,":[19,23,35],"in":[20,64],"particular":[21],"labeled":[22],"often":[25],"hard":[26],"and":[27,161,258],"expensive":[28],"collect.":[30],"To":[31,222],"leverage":[32],"large-scale":[33],"unlabeled":[34],"self-supervised":[36],"learning,":[37,41],"represented":[38],"by":[39,213],"contrastive":[40,47,81,134,153,169,201,214,231,251],"introduced.":[43],"The":[44,193],"objective":[45],"map":[51],"different":[52,69,73],"views":[53,70],"derived":[54,71],"from":[55,72],"a":[56,80],"training":[57],"sample":[58],"(e.g.,":[59],"through":[60,155],"data":[61,89,128,219],"augmentation)":[62],"closer":[63],"their":[65,255],"representation":[66],"space,":[67],"while":[68,208,253],"samples":[74,220],"more":[75,183],"distant.":[76],"In":[77,143],"this":[78,144,224],"way,":[79],"model":[82,259],"learns":[83],"generate":[85],"informative":[86,130],"representations":[87,131],"for":[88,250],"samples,":[90],"which":[91],"are":[92,108,175,203],"then":[93],"used":[94],"perform":[96,147],"downstream":[97],"ML":[98],"tasks.":[99],"Recent":[100],"research":[101],"has":[102],"shown":[103],"that":[104,168,200,242],"models":[107,122,170,202,252],"vulnerable":[109,177,184],"various":[111],"privacy":[112,139,150,257],"attacks.":[113],"most":[115],"current":[118],"efforts":[119],"concentrate":[120],"on":[121,172,236],"trained":[123,171],"with":[124,133],"supervised":[125,191],"learning.":[126],"Meanwhile,":[127],"samples'":[129],"learned":[132],"may":[136],"cause":[137],"severe":[138],"risks":[140,249],"as":[141],"well.":[142],"paper,":[145],"we":[146,226],"first":[149,229],"analysis":[151],"lens":[157],"membership":[159,179,256],"inference":[160,180,187,248],"attribute":[162,186,247],"inference.":[163],"Our":[164],"experimental":[165],"results":[166,240],"show":[167,241],"image":[173],"datasets":[174],"less":[176,204],"attacks":[181,188],"but":[182],"compared":[189],"models.":[192],"former":[194],"due":[196],"fact":[199],"prone":[205],"overfitting,":[207],"latter":[210],"caused":[212],"models'":[215],"capability":[216],"representing":[218],"expressively.":[221],"remedy":[223],"situation,":[225],"propose":[227],"privacy-preserving":[230],"mechanism,":[233],"Talos,":[234],"relying":[235],"adversarial":[237],"training.":[238],"Empirical":[239],"Talos":[243],"can":[244],"successfully":[245],"mitigate":[246],"maintaining":[254],"utility.":[260]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}