{"id":"https://openalex.org/W4410357423","doi":"https://doi.org/10.1145/3672608.3707783","title":"Identity-Focused Inference and Extraction Attacks on Diffusion Models","display_name":"Identity-Focused Inference and Extraction Attacks on Diffusion Models","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4410357423","doi":"https://doi.org/10.1145/3672608.3707783"},"language":"en","primary_location":{"id":"doi:10.1145/3672608.3707783","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3672608.3707783","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707783","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707783","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112360469","display_name":"Jayneel Vora","orcid":"https://orcid.org/0000-0002-0286-6380"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jayneel Vora","raw_affiliation_strings":["University of California, Davis, Davis, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019448790","display_name":"Nader Bouacida","orcid":"https://orcid.org/0000-0002-4571-8484"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nader Bouacida","raw_affiliation_strings":["University of California Davis, Davis, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021635802","display_name":"Aditya Krishnan","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya Krishnan","raw_affiliation_strings":["University of California Davis, Davis, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012989760","display_name":"Prabhu Shankar","orcid":"https://orcid.org/0000-0001-9909-8527"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prabhu Shankar","raw_affiliation_strings":["University of California Davis Health, Davis, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California Davis Health, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086439160","display_name":"Prasant Mohapatra","orcid":"https://orcid.org/0000-0002-2768-5308"},"institutions":[{"id":"https://openalex.org/I2613432","display_name":"University of South Florida","ror":"https://ror.org/032db5x82","country_code":"US","type":"education","lineage":["https://openalex.org/I2613432"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasant Mohapatra","raw_affiliation_strings":["University of South Florida, Tampa, Tampa, FL, USA"],"affiliations":[{"raw_affiliation_string":"University of South Florida, Tampa, Tampa, FL, USA","institution_ids":["https://openalex.org/I2613432"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5112360469"],"corresponding_institution_ids":["https://openalex.org/I84218800"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.052422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1522","last_page":"1530"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9951000213623047,"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":0.9951000213623047,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9926000237464905,"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"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9857000112533569,"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":0.6633355021476746},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6316158175468445},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.6308159828186035},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5731521248817444},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.49854135513305664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36107516288757324},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09566554427146912},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05998161435127258},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.05811154842376709},{"id":"https://openalex.org/keywords/aesthetics","display_name":"Aesthetics","score":0.05594548583030701}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6633355021476746},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6316158175468445},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6308159828186035},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5731521248817444},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.49854135513305664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36107516288757324},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09566554427146912},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05998161435127258},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.05811154842376709},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.05594548583030701},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3672608.3707783","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3672608.3707783","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707783","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3672608.3707783","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3672608.3707783","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707783","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410357423.pdf","grobid_xml":"https://content.openalex.org/works/W4410357423.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W2535690855","https://openalex.org/W3047568746","https://openalex.org/W3096831136","https://openalex.org/W3175528029","https://openalex.org/W3212516020","https://openalex.org/W4297828509","https://openalex.org/W4310695675","https://openalex.org/W4312933868","https://openalex.org/W4361855690","https://openalex.org/W4385269969","https://openalex.org/W4386075893","https://openalex.org/W4386083096","https://openalex.org/W4396877837","https://openalex.org/W6810793953"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W1986418932","https://openalex.org/W2357796999","https://openalex.org/W4321636575","https://openalex.org/W2741131631","https://openalex.org/W2045526782","https://openalex.org/W4405841813","https://openalex.org/W2156919374","https://openalex.org/W1483472507","https://openalex.org/W1984019423"],"abstract_inverted_index":{"The":[0],"increasing":[1],"reliance":[2],"on":[3,59,66,73,119,123,133],"diffusion":[4,142],"models":[5,121],"for":[6,41],"generating":[7],"synthetic":[8],"images":[9],"has":[10],"amplified":[11],"concerns":[12],"about":[13],"the":[14,81,90,113,126,136],"unauthorized":[15],"use":[16],"of":[17,103,110,138],"personal":[18],"data,":[19],"particularly":[20],"facial":[21,75],"images,":[22],"in":[23,45,80],"model":[24,38],"training.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29],"introduce":[30],"a":[31,63],"novel":[32],"identity":[33,114],"inference":[34,55,93,115],"framework":[35],"to":[36,105],"hold":[37],"owners":[39],"accountable":[40],"including":[42],"individuals'":[43],"identities":[44],"their":[46],"training":[47],"data.":[48],"Our":[49],"approach":[50,140],"moves":[51],"beyond":[52],"traditional":[53],"membership":[54,92],"attacks":[56],"by":[57],"focusing":[58],"identity-level":[60],"inference,":[61],"providing":[62],"new":[64],"perspective":[65],"data":[67,127],"privacy":[68],"violations.":[69],"Through":[70],"comprehensive":[71],"evaluations":[72],"two":[74],"image":[76],"datasets,":[77],"Labeled":[78],"Faces":[79],"Wild":[82],"(LFW)":[83],"and":[84,107,125],"CelebA,":[85],"our":[86,139],"experiments":[87],"demonstrate":[88],"that":[89],"proposed":[91],"attack":[94,100,116,129],"surpasses":[95],"baseline":[96],"methods,":[97],"achieving":[98],"an":[99,108],"success":[101],"rate":[102],"up":[104],"89%":[106],"AUC-ROC":[109],"0.91,":[111],"while":[112],"attains":[117],"92%":[118],"LDM":[120],"trained":[122],"LFW,":[124],"extraction":[128],"achieves":[130],"91.6%":[131],"accuracy":[132],"DDPMs,":[134],"validating":[135],"effectiveness":[137],"across":[141],"models.":[143]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}