{"id":"https://openalex.org/W4417136728","doi":"https://doi.org/10.1109/iccv51701.2025.00305","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","display_name":"Adversarial Attention Perturbations for Large Object Detection Transformers","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417136728","doi":"https://doi.org/10.1109/iccv51701.2025.00305"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.02987","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106959218","display_name":"Zachary Yahn","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zachary Yahn","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053032757","display_name":"Selim Furkan Tekin","orcid":"https://orcid.org/0000-0002-8662-3609"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Selim Furkan Tekin","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007420449","display_name":"Fatih \u0130lhan","orcid":"https://orcid.org/0000-0002-0173-7544"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fatih Ilhan","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071522360","display_name":"Sihao Hu","orcid":"https://orcid.org/0000-0003-3297-6991"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sihao Hu","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020135180","display_name":"Tiansheng Huang","orcid":"https://orcid.org/0000-0002-4557-1865"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiansheng Huang","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101968354","display_name":"Yang Xu","orcid":"https://orcid.org/0000-0001-6543-5935"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yichang Xu","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091380057","display_name":"Margaret L. Loper","orcid":"https://orcid.org/0000-0002-0977-696X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I4388482740","display_name":"Georgia Tech Research Institute","ror":"https://ror.org/04qfrh333","country_code":null,"type":"facility","lineage":["https://openalex.org/I130701444","https://openalex.org/I4388482740"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Margaret Loper","raw_affiliation_strings":["Georgia Tech Research Institute,Atlanta,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech Research Institute,Atlanta,USA","institution_ids":["https://openalex.org/I130701444","https://openalex.org/I4388482740"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100343991","display_name":"Ling Liu","orcid":"https://orcid.org/0000-0002-4138-3082"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ling Liu","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.19697766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3184","last_page":"3193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9894000291824341,"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":0.9894000291824341,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0027000000700354576,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.0010000000474974513,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.8230000138282776},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7488999962806702},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6675999760627747},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5400000214576721},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.37540000677108765},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.3336000144481659}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8230000138282776},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7488999962806702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6747000217437744},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6675999760627747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5903000235557556},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5400000214576721},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5142999887466431},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C176856949","wikidata":"https://www.wikidata.org/wiki/Q2001676","display_name":"Offensive","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27000001072883606}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.02987","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.02987","pdf_url":"https://arxiv.org/pdf/2508.02987","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"},{"id":"doi:10.48550/arxiv.2508.02987","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.02987","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.02987","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.02987","pdf_url":"https://arxiv.org/pdf/2508.02987","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6672108330","display_name":null,"funder_award_id":"2302720,2312758","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Adversarial":[0],"perturbations":[1,83,149],"are":[2,18],"useful":[3],"tools":[4],"for":[5,15,51],"exposing":[6],"vulnerabilities":[7],"in":[8,88],"neural":[9],"networks.":[10],"Existing":[11],"adversarial":[12,65,122,131],"perturbation":[13,132],"methods":[14],"object":[16,40,56,154,188],"detection":[17,41,90,140,155,165],"either":[19],"limited":[20],"to":[21,99,157,192],"attacking":[22,52],"CNN-based":[23,60,187],"detectors":[24,57,61,189],"or":[25],"weak":[26,137],"against":[27,39],"transformer-based":[28,55,185],"detectors.":[29],"This":[30,68],"paper":[31,69],"presents":[32],"an":[33,127],"Attention-Focused":[34],"Offensive":[35],"Gradient":[36],"(AFOG)":[37],"attack":[38,103],"transformers.":[42],"By":[43],"design,":[44],"AFOG":[45,75,125,180],"is":[46,105,126,200],"neural-architecture":[47],"agnostic":[48],"and":[49,58,129,146,186,197],"effective":[50],"both":[53],"large":[54,164],"conventional":[59],"with":[62,118,162,194],"a":[63,77],"unified":[64],"attention":[66,79,116],"framework.":[67],"makes":[70],"three":[71],"original":[72],"contributions.":[73],"First,":[74],"utilizes":[76],"learnable":[78,115],"mechanism":[80],"that":[81,179],"focuses":[82],"on":[84,167,184],"vulnerable":[85],"image":[86],"regions":[87],"multi-box":[89],"tasks,":[91],"increasing":[92],"performance":[93],"over":[94],"non-attention":[95],"baselines":[96],"by":[97,107,142,190],"up":[98,191],"30.6%.":[100],"Second,":[101],"AFOG's":[102],"loss":[104,113],"formulated":[106],"integrating":[108],"two":[109],"types":[110],"of":[111,121,139,172],"feature":[112],"through":[114],"updates":[117],"iterative":[119],"injection":[120],"perturbations.":[123],"Finally,":[124],"efficient":[128],"stealthy":[130],"method.":[133],"It":[134],"probes":[135],"the":[136,170],"spots":[138],"transformers":[141,166],"adding":[143],"strategically":[144],"generated":[145],"visually":[147],"imperceptible":[148],"which":[150],"can":[151],"cause":[152],"well-trained":[153],"models":[156],"fail.":[158],"Extensive":[159],"experiments":[160],"conducted":[161],"twelve":[163],"COCO":[168],"demonstrate":[169],"efficacy":[171],"AFOG.":[173],"Our":[174],"empirical":[175],"results":[176],"also":[177],"show":[178],"outperforms":[181],"existing":[182],"attacks":[183],"83%":[193],"superior":[195],"speed":[196],"imperceptibility.":[198],"Code":[199],"available":[201],"at":[202],"https://github.com/zacharyyahn/AFOG.":[203]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}