{"id":"https://openalex.org/W4393335604","doi":"https://doi.org/10.48550/arxiv.2403.19103","title":"Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation","display_name":"Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation","publication_year":2024,"publication_date":"2024-03-28","ids":{"openalex":"https://openalex.org/W4393335604","doi":"https://doi.org/10.48550/arxiv.2403.19103"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2403.19103","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.19103","pdf_url":"https://arxiv.org/pdf/2403.19103","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":"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.19103","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100457867","display_name":"Yutong He","orcid":"https://orcid.org/0000-0001-6082-0615"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"He, Yutong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028501158","display_name":"Alexander Robey","orcid":"https://orcid.org/0009-0003-5693-2819"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robey, Alexander","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031225419","display_name":"Naoki Murata","orcid":"https://orcid.org/0000-0001-7418-5173"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murata, Naoki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011289358","display_name":"Yiding Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Yiding","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027087182","display_name":"Joshua Williams","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Williams, Joshua Nathaniel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029243115","display_name":"George J. Pappas","orcid":"https://orcid.org/0000-0001-9081-0637"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pappas, George J.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059354479","display_name":"Hamed Hassani","orcid":"https://orcid.org/0000-0002-9448-8750"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hassani, Hamed","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mitsufuji, Yuki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071983998","display_name":"Ruslan Salakhutdinov","orcid":"https://orcid.org/0000-0002-3752-2756"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Salakhutdinov, Ruslan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075035644","display_name":"J. Zico Kolter","orcid":"https://orcid.org/0000-0002-8106-5759"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kolter, J. Zico","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5100457867"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.8270999789237976,"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"}},"topics":[{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.8270999789237976,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.7730000019073486,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12720","display_name":"Multimedia Communication and Technology","score":0.7620999813079834,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.7455946803092957},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6011982560157776},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5762902498245239},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.46584805846214294},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.39131760597229004},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.35695457458496094},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3393934369087219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32107052206993103},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3202046751976013}],"concepts":[{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.7455946803092957},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6011982560157776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5762902498245239},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.46584805846214294},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39131760597229004},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.35695457458496094},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3393934369087219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32107052206993103},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3202046751976013}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2403.19103","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.19103","pdf_url":"https://arxiv.org/pdf/2403.19103","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":"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.2403.19103","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.19103","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.19103","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.19103","pdf_url":"https://arxiv.org/pdf/2403.19103","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":"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2047881532","https://openalex.org/W2285795935","https://openalex.org/W4389072557","https://openalex.org/W4319452366","https://openalex.org/W4293695278","https://openalex.org/W2727407240","https://openalex.org/W3013663659","https://openalex.org/W3197218948","https://openalex.org/W2141612310","https://openalex.org/W2994097316"],"abstract_inverted_index":{"Prompt":[0],"engineering":[1],"is":[2],"an":[3,56],"effective":[4],"but":[5],"labor-intensive":[6],"way":[7],"to":[8,42,75,93],"control":[9],"text-to-image":[10],"(T2I)":[11],"generative":[12],"models.":[13,77],"Its":[14],"time-intensive":[15],"nature":[16],"and":[17,62,110,121,131],"complexity":[18],"have":[19],"spurred":[20],"the":[21,43,87,96,102,108],"development":[22],"of":[23,91,112],"algorithms":[24],"for":[25,118],"automated":[26],"prompt":[27,98],"generation.":[28],"However,":[29],"these":[30],"methods":[31],"often":[32],"struggle":[33],"with":[34],"transferability":[35],"across":[36,123],"T2I":[37,76,125],"models,":[38,126],"require":[39],"white-box":[40],"access":[41,74],"underlying":[44],"model,":[45],"or":[46],"produce":[47],"non-intuitive":[48],"prompts.":[49],"In":[50],"this":[51],"work,":[52],"we":[53],"introduce":[54],"PRISM,":[55],"algorithm":[57],"that":[58,65],"automatically":[59],"produces":[60],"human-interpretable":[61],"transferable":[63],"prompts":[64,117],"can":[66],"effectively":[67],"generate":[68],"desired":[69],"concepts":[70],"given":[71],"only":[72],"black-box":[73],"Inspired":[78],"by":[79],"large":[80],"language":[81],"model":[82],"(LLM)":[83],"jailbreaking,":[84],"PRISM":[85,113],"leverages":[86],"in-context":[88],"learning":[89],"ability":[90],"LLMs":[92],"iteratively":[94],"refine":[95],"candidate":[97],"distribution":[99],"built":[100],"upon":[101],"reference":[103],"images.":[104],"Our":[105],"experiments":[106],"demonstrate":[107],"versatility":[109],"effectiveness":[111],"in":[114],"generating":[115],"accurate":[116],"objects,":[119],"styles,":[120],"images":[122],"multiple":[124],"including":[127],"Stable":[128],"Diffusion,":[129],"DALL-E,":[130],"Midjourney.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}