{"id":"https://openalex.org/W4403662628","doi":"https://doi.org/10.1145/3658644.3690327","title":"Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based Policies","display_name":"Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based Policies","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4403662628","doi":"https://doi.org/10.1145/3658644.3690327"},"language":"en","primary_location":{"id":"doi:10.1145/3658644.3690327","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658644.3690327","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3658644.3690327","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 2024 on ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3658644.3690327","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102749927","display_name":"Peiran Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiran Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6881-2855","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091137864","display_name":"Qiyu Li","orcid":"https://orcid.org/0009-0004-5174-9844"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiyu Li","raw_affiliation_strings":["University of California, San Diego, San Diego, USA"],"raw_orcid":"https://orcid.org/0009-0004-5174-9844","affiliations":[{"raw_affiliation_string":"University of California, San Diego, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032823880","display_name":"Longxuan Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Longxuan Yu","raw_affiliation_strings":["University of California, San Diego, San Diego, USA"],"raw_orcid":"https://orcid.org/0009-0001-7793-9994","affiliations":[{"raw_affiliation_string":"University of California, San Diego, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054424294","display_name":"Ziyao Wang","orcid":"https://orcid.org/0000-0002-1394-9587"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyao Wang","raw_affiliation_strings":["University of Maryland College Park, College Park, USA"],"raw_orcid":"https://orcid.org/0000-0002-1394-9587","affiliations":[{"raw_affiliation_string":"University of Maryland College Park, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413615","display_name":"Ang Li","orcid":"https://orcid.org/0000-0002-4990-1729"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ang Li","raw_affiliation_strings":["University of Maryland College Park, College Park, USA"],"raw_orcid":"https://orcid.org/0000-0002-4990-1729","affiliations":[{"raw_affiliation_string":"University of Maryland College Park, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032046097","display_name":"Haojian Jin","orcid":"https://orcid.org/0000-0001-5212-2235"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haojian Jin","raw_affiliation_strings":["University of California, San Diego, San Diego, USA"],"raw_orcid":"https://orcid.org/0000-0001-5212-2235","affiliations":[{"raw_affiliation_string":"University of California, San Diego, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6109,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74645291,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1181","last_page":"1195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.986299991607666,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.986299991607666,"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/T10028","display_name":"Topic Modeling","score":0.9854999780654907,"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/T13157","display_name":"Cancer-related gene regulation","score":0.9474999904632568,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/moderation","display_name":"Moderation","score":0.967901349067688},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7286149859428406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7042286396026611},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6241205930709839},{"id":"https://openalex.org/keywords/moderated-mediation","display_name":"Moderated mediation","score":0.5308483839035034},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5245183706283569},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47366008162498474},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35147756338119507},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3255477845668793},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.303385853767395},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14845383167266846},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0698041319847107}],"concepts":[{"id":"https://openalex.org/C93225998","wikidata":"https://www.wikidata.org/wiki/Q1941972","display_name":"Moderation","level":2,"score":0.967901349067688},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7286149859428406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7042286396026611},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6241205930709839},{"id":"https://openalex.org/C24614281","wikidata":"https://www.wikidata.org/wiki/Q17086331","display_name":"Moderated mediation","level":2,"score":0.5308483839035034},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5245183706283569},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47366008162498474},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35147756338119507},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3255477845668793},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.303385853767395},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14845383167266846},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0698041319847107},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems 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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3658644.3690327","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658644.3690327","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3658644.3690327","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 2024 on ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2408.07728","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.07728","pdf_url":"https://arxiv.org/pdf/2408.07728","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3658644.3690327","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658644.3690327","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3658644.3690327","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 2024 on ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403662628.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1488996941","https://openalex.org/W1993692165","https://openalex.org/W2032191478","https://openalex.org/W2535001381","https://openalex.org/W2985913519","https://openalex.org/W2991138171","https://openalex.org/W3022659481","https://openalex.org/W3023153742","https://openalex.org/W3032708546","https://openalex.org/W3035063907","https://openalex.org/W3129093240","https://openalex.org/W3191136298","https://openalex.org/W3210951978","https://openalex.org/W4212774754","https://openalex.org/W4281645553","https://openalex.org/W4285077774","https://openalex.org/W4287363917","https://openalex.org/W4288057811","https://openalex.org/W4291220705","https://openalex.org/W4296562799","https://openalex.org/W4308381127","https://openalex.org/W4312933868","https://openalex.org/W4385412489","https://openalex.org/W4386066154","https://openalex.org/W4386066536","https://openalex.org/W4386075682","https://openalex.org/W4387606461","https://openalex.org/W4388857623","https://openalex.org/W4388858443","https://openalex.org/W4388858734","https://openalex.org/W4388858946","https://openalex.org/W4388867373"],"related_works":["https://openalex.org/W2740268725","https://openalex.org/W3093710306","https://openalex.org/W750217911","https://openalex.org/W2129951714","https://openalex.org/W2969304181","https://openalex.org/W2073279551","https://openalex.org/W3173888843","https://openalex.org/W2586037687","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"We":[0,133],"present":[1],"Moderator,":[2],"a":[3,22,81],"policy-based":[4],"model":[5,25,46,90,108,120],"management":[6],"system":[7],"that":[8,37,94,171],"allows":[9,58],"administrators":[10],"to":[11,26,34,43,60,91,96,104,109,125,139,154,197],"specify":[12,61],"fine-grained":[13],"content":[14,63,181],"moderation":[15,77,114],"policies":[16,153],"and":[17,75,115,145,151,185],"modify":[18],"the":[19,39,54,88,107,118,122,141,187],"weights":[20],"of":[21,83,143,176,192],"text-to-image":[23],"(TTI)":[24],"make":[27],"it":[28,71],"significantly":[29],"more":[30,195],"challenging":[31],"for":[32,113],"users":[33,169,177,189],"produce":[35],"images":[36,93,103],"violate":[38],"policies.":[40],"In":[41],"contrast":[42],"existing":[44],"general-purpose":[45],"editing":[47],"techniques,":[48],"which":[49,68],"unlearn":[50],"concepts":[51],"without":[52],"considering":[53],"associated":[55],"contexts,":[56],"Moderator":[57,85,135,172],"admins":[59,144],"what":[62],"should":[64,72],"be":[65,73,97],"moderated,":[66,74,98],"under":[67,182],"context,":[69],"how":[70],"why":[76],"is":[78],"necessary.":[79],"Given":[80],"set":[82],"policies,":[84],"first":[86],"prompts":[87],"original":[89,119],"generate":[92,198],"need":[95],"then":[99],"uses":[100],"these":[101],"self-generated":[102],"reverse":[105],"fine-tune":[106],"compute":[110],"task":[111,123],"vectors":[112,124],"finally":[116],"negates":[117],"with":[121,136,165],"decrease":[126],"its":[127],"performance":[128],"in":[129,158],"generating":[130,179],"moderated":[131,180],"content.":[132,200],"evaluated":[134],"14":[137],"participants":[138],"play":[140],"role":[142],"found":[146],"they":[147],"could":[148],"quickly":[149],"learn":[150],"author":[152],"pass":[155],"unit":[156],"tests":[157],"approximately":[159],"2.29":[160],"policy":[161],"iterations.":[162],"Our":[163],"experiment":[164],"32":[166],"stable":[167],"diffusion":[168],"suggested":[170],"can":[173],"prevent":[174],"65%":[175],"from":[178],"15":[183],"attempts":[184,196],"require":[186],"remaining":[188],"an":[190],"average":[191],"8.3":[193],"times":[194],"undesired":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
