{"id":"https://openalex.org/W4396790418","doi":"https://doi.org/10.1109/satml59370.2024.00010","title":"Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk","display_name":"Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk","alternate_titles":[],"publication_year":2024,"publication_date":"2024-04-09","ids":{"openalex":"https://openalex.org/W4396790418","doi":"https://doi.org/10.1109/satml59370.2024.00010"},"language":"en","primary_location":{"id":"doi:10.1109/satml59370.2024.00010","doi":"https://doi.org/10.1109/satml59370.2024.00010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/satml59370.2024.00010","pdf_url":null,"source":{"id":"https://openalex.org/S7407087861","display_name":"IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W4396790418"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.09450","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhangheng Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhangheng Li","raw_affiliation_strings":["University of Texas, Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas, Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071064449","display_name":"Junyuan Hong","orcid":"https://orcid.org/0000-0002-5718-5187","observed_orcids":["https://orcid.org/0000-0002-5718-5187"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junyuan Hong","raw_affiliation_strings":["University of Texas, Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas, Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bo Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["University of Illinois Urbana-Champaign","University of Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048522863","display_name":"Zhangyang Wang","orcid":"https://orcid.org/0000-0002-2050-5693","observed_orcids":["https://orcid.org/0000-0002-2050-5693"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhangyang Wang","raw_affiliation_strings":["University of Texas, Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas, Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6791,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.92498013,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"18","last_page":"32"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.6640999913215637,"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":0.6640999913215637,"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":0.301800012588501,"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":0.021900000050663948,"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/diffusion-models","display_name":"diffusion models","score":0.921999990940094},{"id":"https://openalex.org/keywords/membership-inference-attacks","display_name":"membership inference attacks","score":0.7639999985694885},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.7300000190734863},{"id":"https://openalex.org/keywords/training-data-leakage","display_name":"training data leakage","score":0.7170000076293945},{"id":"https://openalex.org/keywords/dreambooth","display_name":"DreamBooth","score":0.8960000276565552},{"id":"https://openalex.org/keywords/textual-inversion","display_name":"textual inversion","score":0.9660000205039978},{"id":"https://openalex.org/keywords/lora","display_name":"LoRa","score":0.9909999966621399},{"id":"https://openalex.org/keywords/hypernetworks","display_name":"hypernetworks","score":0.9300000071525574},{"id":"https://openalex.org/keywords/parameter-efficient-fine-tuning","display_name":"parameter-efficient fine-tuning","score":0.7559999823570251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7578864097595215},{"id":"https://openalex.org/C2779053110","wikidata":"https://www.wikidata.org/wiki/Q7462601","display_name":"Shake","level":2,"score":0.7495540380477905},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6749539375305176},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5552105903625488},{"id":"https://openalex.org/C2780378346","wikidata":"https://www.wikidata.org/wiki/Q1349983","display_name":"Leak","level":2,"score":0.5537277460098267},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4911057949066162},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4608802795410156},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.4153103232383728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3400822877883911},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.320550799369812},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2643589377403259},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09429830312728882},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/satml59370.2024.00010","doi":"https://doi.org/10.1109/satml59370.2024.00010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/satml59370.2024.00010","pdf_url":null,"source":{"id":"https://openalex.org/S7407087861","display_name":"IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2403.09450","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.09450","pdf_url":"https://arxiv.org/pdf/2403.09450","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.09450","doi":"https://doi.org/10.48550/arxiv.2403.09450","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.09450","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.09450","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.09450","pdf_url":"https://arxiv.org/pdf/2403.09450","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2882411384","display_name":"AF: Small: Collaborative Research: Rigorous Approaches for Scalable Privacy-preserving Deep Learning","funder_award_id":"1910100","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6197153243","display_name":null,"funder_award_id":"2229876","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G6360409883","display_name":"AI Institute for Agent-based Cyber Threat Intelligence and Operation","funder_award_id":"2229876","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6860822721","display_name":null,"funder_award_id":"80NSSC20M0229","funder_id":"https://openalex.org/F4320306101","funder_display_name":"National Aeronautics and Space Administration"},{"id":"https://openalex.org/G7337221845","display_name":"Collaborative Research: III: Medium: A consolidated framework of computational privacy and machine learning","funder_award_id":"2212176","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7894451278","display_name":"CAREER: DeepTrust: Enabling Robust Machine Learning with Exogenous Information","funder_award_id":"2046726","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"},{"id":"https://openalex.org/F4320310620","display_name":"University of Texas at Austin","ror":"https://ror.org/00hj54h04"},{"id":"https://openalex.org/F4320322037","display_name":"Nuclear Safety and Security Commission","ror":"https://ror.org/05qk3ge34"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396790418.pdf","grobid_xml":"https://content.openalex.org/works/W4396790418.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1873763122","https://openalex.org/W2473418344","https://openalex.org/W2775190420","https://openalex.org/W2964121744","https://openalex.org/W3036167779","https://openalex.org/W3128522081","https://openalex.org/W3135367836","https://openalex.org/W3168867926","https://openalex.org/W3191581723","https://openalex.org/W4210288991","https://openalex.org/W4224035735","https://openalex.org/W4281485151","https://openalex.org/W4282813466","https://openalex.org/W4288057780","https://openalex.org/W4288099256","https://openalex.org/W4289655479","https://openalex.org/W4289785095","https://openalex.org/W4302012908","https://openalex.org/W4306820534","https://openalex.org/W4312749295","https://openalex.org/W4312933868","https://openalex.org/W4318144071","https://openalex.org/W4318719586","https://openalex.org/W4319166710","https://openalex.org/W4322717491","https://openalex.org/W4377695098","https://openalex.org/W4386071613","https://openalex.org/W4386072096","https://openalex.org/W4386076098","https://openalex.org/W4389195517","https://openalex.org/W4389500732","https://openalex.org/W4399971973","https://openalex.org/W4400019960","https://openalex.org/W6796581206","https://openalex.org/W6846007759","https://openalex.org/W6890057398","https://openalex.org/W7133185348","https://openalex.org/W7133241521"],"related_works":["https://openalex.org/W4403661807","https://openalex.org/W7172276207","https://openalex.org/W4389195517","https://openalex.org/W7161623858","https://openalex.org/W7126197959","https://openalex.org/W4408750093","https://openalex.org/W4321176305","https://openalex.org/W4318144071","https://openalex.org/W4318719586","https://openalex.org/W4409475022"],"abstract_inverted_index":{"While":[0],"diffusion":[1,66,100,133],"models":[2,17,44,101,134],"have":[3],"recently":[4],"demonstrated":[5],"remarkable":[6],"progress":[7],"in":[8,60],"generating":[9],"realistic":[10],"images,":[11],"privacy":[12,52,130],"risks":[13],"also":[14],"arise:":[15],"published":[16],"or":[18],"APIs":[19],"could":[20,58],"generate":[21],"training":[22,28],"images":[23],"and":[24,72,75,79,107],"thus":[25],"leak":[26],"privacy-sensitive":[27],"information.":[29],"In":[30,86],"this":[31],"paper,":[32],"we":[33],"reveal":[34],"a":[35],"new":[36],"risk,":[37],"Shake-to-Leak":[38],"(S2L),":[39],"that":[40,56,128],"fine-tuning":[41,63],"the":[42,50,87,93,129],"pre-trained":[43],"with":[45,132],"manipulated":[46],"data":[47],"can":[48,91,108],"amplify":[49,92],"existing":[51],"risks.":[53],"We":[54],"demonstrate":[55],"S2L":[57,90],"occur":[59],"various":[61],"standard":[62],"strategies":[64],"for":[65],"models,":[67],"including":[68],"concept-injection":[69],"methods":[70,77],"(DreamBooth":[71],"Textual":[73],"Inversion)":[74],"parameter-efficient":[76],"(LoRA":[78],"Hypernetwork),":[80],"as":[81,83],"well":[82],"their":[84],"combinations.":[85],"worst":[88],"case,":[89],"state-of-the-art":[94],"membership":[95],"inference":[96],"attack":[97],"(MIA)":[98],"on":[99,120],"by":[102],"5.4%":[103],"(absolute":[104],"difference)":[105],"AUC":[106],"increase":[109],"extracted":[110],"private":[111],"samples":[112,116,119],"from":[113],"almost":[114],"0":[115],"to":[117],"16.3":[118],"average":[121],"per":[122],"target":[123],"domain.":[124],"This":[125],"discovery":[126],"underscores":[127],"risk":[131],"is":[135],"even":[136],"more":[137],"severe":[138],"than":[139],"previously":[140],"recognized.":[141],"Codes":[142],"are":[143],"available":[144],"at":[145],"https://github.com/VITA-Group/Shake-to-Leak.":[146]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4396790418","counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":11}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2024-05-11T00:00:00"}
