{"id":"https://openalex.org/W4415538161","doi":"https://doi.org/10.1145/3746027.3755755","title":"Immunizing Images from Text to Image Editing via Adversarial Cross-Attention","display_name":"Immunizing Images from Text to Image Editing via Adversarial Cross-Attention","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538161","doi":"https://doi.org/10.1145/3746027.3755755"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755755","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755755","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755755","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119759061","display_name":"Matteo Trippodo","orcid":null},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Matteo Trippodo","raw_affiliation_strings":["University of Florence, Florence, Italy"],"raw_orcid":"https://orcid.org/0009-0009-4744-7110","affiliations":[{"raw_affiliation_string":"University of Florence, Florence, Italy","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065891142","display_name":"Federico Becattini","orcid":"https://orcid.org/0000-0003-2537-2700"},"institutions":[{"id":"https://openalex.org/I102064193","display_name":"University of Siena","ror":"https://ror.org/01tevnk56","country_code":"IT","type":"education","lineage":["https://openalex.org/I102064193"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Federico Becattini","raw_affiliation_strings":["University of Siena, Siena, Italy"],"raw_orcid":"https://orcid.org/0000-0003-2537-2700","affiliations":[{"raw_affiliation_string":"University of Siena, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043288749","display_name":"Lorenzo Seidenari","orcid":"https://orcid.org/0000-0003-4816-0268"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Seidenari","raw_affiliation_strings":["University of Florence, Florence, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4816-0268","affiliations":[{"raw_affiliation_string":"University of Florence, Florence, Italy","institution_ids":["https://openalex.org/I45084792"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39364705,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10535","last_page":"10543"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9986000061035156,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9983000159263611,"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/image-editing","display_name":"Image editing","score":0.7469000220298767},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6748999953269958},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5144000053405762},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47429999709129333},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.45910000801086426},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45660001039505005},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.36800000071525574},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.35929998755455017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8185999989509583},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.7469000220298767},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6748999953269958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6139000058174133},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5144000053405762},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47429999709129333},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45660001039505005},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4345000088214874},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.35929998755455017},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3499999940395355},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.34439998865127563},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32420000433921814},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.31769999861717224},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.3086000084877014},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.25699999928474426},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755755","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755755","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:flore.unifi.it:2158/1439409","is_oa":true,"landing_page_url":"https://hdl.handle.net/2158/1439409","pdf_url":null,"source":{"id":"https://openalex.org/S4306402033","display_name":"Florence Research (University of Florence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45084792","host_organization_name":"University of Florence","host_organization_lineage":["https://openalex.org/I45084792"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755755","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755755","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W4312933868","https://openalex.org/W4360884927","https://openalex.org/W4396788055","https://openalex.org/W4402753991"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"text-based":[3],"image":[4,59,69,86],"editing":[5,39,96,100,155],"have":[6],"enabled":[7],"fine-grained":[8],"manipulation":[9],"of":[10,38,57,66,84,94,106],"visual":[11,36,55],"content":[12],"guided":[13],"by":[14,60],"natural":[15],"language.":[16],"However,":[17],"such":[18],"methods":[19],"are":[20],"susceptible":[21],"to":[22],"adversarial":[23,127],"attacks.":[24],"In":[25],"this":[26],"work,":[27],"we":[28,112],"propose":[29,113],"a":[30,50,71],"novel":[31,115],"attack":[32,152],"that":[33,150],"targets":[34],"the":[35,47,54,58,67,74,79,82,85,95,99,104,146],"component":[37],"methods.":[40],"We":[41],"introduce":[42],"Attention":[43],"Attack,":[44],"which":[45,120,135],"disrupts":[46],"cross-attention":[48],"between":[49,81,124],"textual":[51,89],"prompt":[52],"and":[53,87,126,129],"representation":[56],"using":[61],"an":[62],"automatically":[63],"generated":[64],"caption":[65],"source":[68],"as":[70],"proxy":[72],"for":[73,109],"edit":[75],"prompt.":[76,101],"This":[77],"breaks":[78],"alignment":[80],"contents":[83],"their":[88],"description,":[90],"without":[91],"requiring":[92],"knowledge":[93],"method":[97],"or":[98],"Reflecting":[102],"on":[103,145],"reliability":[105],"existing":[107],"metrics":[108],"immunization":[110],"success,":[111],"two":[114],"evaluation":[116],"strategies:":[117],"Caption":[118],"Similarity,":[119],"quantifies":[121],"semantic":[122,130],"consistency":[123],"original":[125],"edits,":[128],"Intersection":[131],"over":[132],"Union":[133],"(IoU),":[134],"measures":[136],"spatial":[137],"layout":[138],"disruption":[139],"via":[140],"segmentation":[141],"masks.":[142],"Experiments":[143],"conducted":[144],"TEDBench++":[147],"benchmark":[148],"demonstrate":[149],"our":[151],"significantly":[153],"degrades":[154],"performance":[156],"while":[157],"remaining":[158],"imperceptible.":[159]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}