{"id":"https://openalex.org/W4401943782","doi":"https://doi.org/10.1109/iccp61108.2024.10644615","title":"Deepmarking: Leveraging Adversarial Noise for Membership Inference Attacks","display_name":"Deepmarking: Leveraging Adversarial Noise for Membership Inference Attacks","publication_year":2024,"publication_date":"2024-07-22","ids":{"openalex":"https://openalex.org/W4401943782","doi":"https://doi.org/10.1109/iccp61108.2024.10644615"},"language":"en","primary_location":{"id":"doi:10.1109/iccp61108.2024.10644615","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iccp61108.2024.10644615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Computational Photography (ICCP)","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/A5093274753","display_name":"Malthe Andreas Lejb\u00f8lle Jelstrup","orcid":null},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Malthe Andreas Lejb\u00f8lle Jelstrup","raw_affiliation_strings":["Technical University of Denmark,Visual Compute Section,Compute Department"],"affiliations":[{"raw_affiliation_string":"Technical University of Denmark,Visual Compute Section,Compute Department","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024315163","display_name":"Siavash Bigdeli","orcid":"https://orcid.org/0000-0003-2569-6473"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Siavash Arjomand Bigdeli","raw_affiliation_strings":["Technical University of Denmark,Visual Compute Section,Compute Department"],"affiliations":[{"raw_affiliation_string":"Technical University of Denmark,Visual Compute Section,Compute Department","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5093274753"],"corresponding_institution_ids":["https://openalex.org/I96673099"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1185344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":null,"first_page":"1","last_page":"10"},"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":0.9991999864578247,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9796000123023987,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.9070712327957153},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7222599983215332},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7014984488487244},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6148281693458557},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.4554753303527832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4429386258125305},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32316961884498596}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9070712327957153},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7222599983215332},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7014984488487244},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6148281693458557},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4554753303527832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4429386258125305},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32316961884498596},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccp61108.2024.10644615","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iccp61108.2024.10644615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Computational Photography (ICCP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2051267297","https://openalex.org/W2103559027","https://openalex.org/W2535690855","https://openalex.org/W2551176409","https://openalex.org/W2806082141","https://openalex.org/W2952126211","https://openalex.org/W2962995403","https://openalex.org/W2970534682","https://openalex.org/W3035527820","https://openalex.org/W3035671550","https://openalex.org/W3138815606","https://openalex.org/W4283070861","https://openalex.org/W4288057780","https://openalex.org/W4308643663","https://openalex.org/W4312076541","https://openalex.org/W4312872760","https://openalex.org/W4383860818","https://openalex.org/W4384112166","https://openalex.org/W4386831200","https://openalex.org/W6739868092","https://openalex.org/W6764891227","https://openalex.org/W6779259321","https://openalex.org/W6787972765","https://openalex.org/W6810216544","https://openalex.org/W6853539036"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4288019534"],"abstract_inverted_index":{"The":[0,136],"performance":[1,82],"and":[2,146],"inference":[3],"capabilities":[4],"of":[5,33,57,76,83,98,103,138,144,151],"neural":[6,51,84,157],"networks":[7],"rely":[8],"heavily":[9],"on":[10],"the":[11,30,46,74,81,133,142,148,162,171,176],"training":[12,31,105,125,159],"data":[13,38,41,58,99,153],"they":[14],"are":[15],"exposed":[16],"to.":[17],"Generally,":[18],"larger":[19],"dataset":[20],"yield":[21],"more":[22],"powerful":[23],"models.":[24],"This":[25,71],"incentive":[26],"to":[27,37,49,65,67,79,93,112],"continuously":[28],"extend":[29],"sets":[32],"models":[34],"can":[35,90],"lead":[36],"exploitation,":[39],"where":[40,170],"is":[42,59,62,100],"being":[43],"used":[44,92],"against":[45],"owner's":[47],"wishes":[48],"train":[50],"networks.":[52],"Even":[53],"if":[54],"such":[55],"misuse":[56],"suspected,":[60],"it":[61],"currently":[63],"next":[64],"impossible":[66],"determine":[68],"its":[69,121],"veracity.":[70],"research":[72],"explores":[73],"utilization":[75],"adversarial":[77,117],"noise":[78,118],"manipulate":[80],"networks,":[85],"investigating":[86],"how":[87],"those":[88],"findings":[89,137],"be":[91],"infer":[94],"whether":[95],"a":[96,101,104,109,124,152,156,166],"collection":[97,154],"member":[102],"set.":[106],"It":[107],"proposes":[108],"novel":[110],"approach":[111],"generate":[113],"\u201cdeepmarked\u201d":[114],"images":[115],"containing":[116],"that":[119],"maximizes":[120],"detectability":[122],"as":[123],"set":[126,160],"member,":[127],"while":[128],"remaining":[129],"visually":[130],"indistinguishable":[131],"from":[132],"original":[134],"data.":[135],"this":[139],"study":[140],"demonstrate":[141],"feasibility":[143],"detecting":[145],"inferring":[147],"membership":[149],"status":[150],"within":[155],"network's":[158],"using":[161],"proposed":[163],"technique,":[164],"in":[165],"restricted":[167],"black-box":[168],"setting":[169],"model":[172],"output":[173],"only":[174],"contains":[175],"single":[177],"highest":[178],"likelihood":[179],"class.":[180]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}