{"id":"https://openalex.org/W7164888959","doi":"https://doi.org/10.1145/3785353.3815073","title":"Comparative Study of Adversarial Training and Randomized Smoothing for Robust AI-Generated Image Attribution","display_name":"Comparative Study of Adversarial Training and Randomized Smoothing for Robust AI-Generated Image Attribution","publication_year":2026,"publication_date":"2026-06-16","ids":{"openalex":"https://openalex.org/W7164888959","doi":"https://doi.org/10.1145/3785353.3815073"},"language":null,"primary_location":{"id":"doi:10.1145/3785353.3815073","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785353.3815073","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 2026 ACM Workshop on Information Hiding and Multimedia Security","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3785353.3815073","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080049509","display_name":"Kai Zeng","orcid":"https://orcid.org/0009-0007-6275-9767"},"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":"Kai Zeng","raw_affiliation_strings":["Department of Information engineering and mathematics, University of Siena, Siena, Italy"],"raw_orcid":"https://orcid.org/0009-0007-6275-9767","affiliations":[{"raw_affiliation_string":"Department of Information engineering and mathematics, University of Siena, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091342001","display_name":"Niccol\u00f2 Pancino","orcid":"https://orcid.org/0000-0003-2212-4728"},"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":"Niccol\u00f2 Pancino","raw_affiliation_strings":["Department of Information engineering and mathematics, University of Siena, Siena, Italy"],"raw_orcid":"https://orcid.org/0000-0003-2212-4728","affiliations":[{"raw_affiliation_string":"Department of Information engineering and mathematics, University of Siena, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138714578","display_name":"Nasrin Malekzadeh Goradel","orcid":"https://orcid.org/0009-0008-9672-6418"},"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":"Nasrin Malekzadeh Goradel","raw_affiliation_strings":["Department of Information engineering and mathematics, University of Siena, Siena, Italy"],"raw_orcid":"https://orcid.org/0009-0008-9672-6418","affiliations":[{"raw_affiliation_string":"Department of Information engineering and mathematics, University of Siena, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007836692","display_name":"Mauro Barni","orcid":"https://orcid.org/0000-0002-7368-0866"},"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":"Mauro Barni","raw_affiliation_strings":["Department of Information engineering and mathematics, University of Siena, Siena, Italy"],"raw_orcid":"https://orcid.org/0000-0002-7368-0866","affiliations":[{"raw_affiliation_string":"Department of Information engineering and mathematics, University of Siena, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026139768","display_name":"Benedetta Tondi","orcid":"https://orcid.org/0000-0002-7518-046X"},"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":"Benedetta Tondi","raw_affiliation_strings":["Department of Information engineering and mathematics, University of Siena, Siena, Italy"],"raw_orcid":"https://orcid.org/0000-0002-7518-046X","affiliations":[{"raw_affiliation_string":"Department of Information engineering and mathematics, University of Siena, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102064193"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69209693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"40","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9075000286102295,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9075000286102295,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.03720000013709068,"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":0.01640000008046627,"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/adversarial-system","display_name":"Adversarial system","score":0.859000027179718},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.742900013923645},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.7215999960899353},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.40310001373291016},{"id":"https://openalex.org/keywords/attribution","display_name":"Attribution","score":0.3319000005722046}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.859000027179718},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.742900013923645},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.7215999960899353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.705299973487854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6398000121116638},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5195000171661377},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3149999976158142},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29409998655319214},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.28220000863075256}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3785353.3815073","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785353.3815073","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 2026 ACM Workshop on Information Hiding and Multimedia Security","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3785353.3815073","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785353.3815073","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 2026 ACM Workshop on Information Hiding and Multimedia Security","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W4388858946","https://openalex.org/W4399556754","https://openalex.org/W4413861819","https://openalex.org/W4417052041","https://openalex.org/W7082286678"],"related_works":[],"abstract_inverted_index":{"In":[0,134],"this":[1],"paper":[2],"we":[3],"explore":[4],"two":[5,112],"different":[6],"approaches":[7,120],"for":[8,63,72],"designing":[9],"AI-generated":[10,115],"image":[11,48,132],"attribution":[12,49],"methods":[13],"that":[14,118],"are":[15],"robust":[16],"in":[17,34],"adversarial":[18,21,40,123,136,156],"settings,":[19],"namely":[20],"training":[22,137],"(AT)":[23],"and":[24,125],"randomized":[25,149],"smoothing":[26,150],"(RS).":[27],"While":[28],"AT":[29],"has":[30,58,104],"been":[31,106],"widely":[32],"adopted":[33],"machine":[35],"learning":[36,66],"to":[37,46,101,130],"improve":[38],"the":[39,55,85,89,92],"robustness":[41,78,124,140,154],"of":[42,77,84,94,114,145],"classifiers,":[43],"its":[44,99],"application":[45,100],"source":[47],"is":[50],"still":[51],"unexplored.":[52],"RS,":[53],"on":[54,111],"other":[56],"hand,":[57],"emerged":[59],"as":[60],"a":[61,74,95,127,142],"method":[62],"developing":[64],"deep":[65],"classifiers":[67],"with":[68],"certified":[69,75],"robustness,":[70],"i.e.,":[71],"which":[73],"level":[76],"can":[79],"be":[80],"theoretically":[81],"guaranteed,":[82],"regardless":[83],"specific":[86],"manipulation":[87],"causing":[88],"distortion.":[90],"With":[91],"exception":[93],"single":[96],"prior":[97],"study,":[98],"forensic":[102],"tasks":[103],"not":[105],"previously":[107],"explored.":[108],"Experiments":[109],"conducted":[110],"datasets":[113],"images":[116],"show":[117],"both":[119],"achieve":[121],"substantial":[122],"exhibit":[126],"general":[128],"resistance":[129],"common":[131],"manipulations.":[133],"particular,":[135],"provides":[138],"stronger":[139],"against":[141,155],"broad":[143],"range":[144],"post-processing":[146],"operations,":[147],"whereas":[148],"yields":[151],"higher":[152],"practical":[153],"attacks.":[157]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-06-17T00:00:00"}