{"id":"https://openalex.org/W7170736384","doi":"https://doi.org/10.48550/arxiv.2607.21243","title":"Detectors Learn the Wrong Thing: Shortcut-Resistant Adversarial Training Against Physically Realizable Attacks","display_name":"Detectors Learn the Wrong Thing: Shortcut-Resistant Adversarial Training Against Physically Realizable Attacks","publication_year":2026,"publication_date":"2026-07-23","ids":{"openalex":"https://openalex.org/W7170736384","doi":"https://doi.org/10.48550/arxiv.2607.21243"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.21243","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.21243","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.21243","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5143543316","display_name":"Yuanhao Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yuanhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143557571","display_name":"Yilong Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Yilong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143597558","display_name":"Jinlei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jinlei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143553018","display_name":"Xuesong Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Xuesong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143535895","display_name":"Zheng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5143596306","display_name":"Haiyang Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Haiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9966999888420105,"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":0.9966999888420105,"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":0.0007999999797903001,"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":0.00039999998989515007,"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":0.8873000144958496},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6313999891281128},{"id":"https://openalex.org/keywords/texture","display_name":"Texture (cosmology)","score":0.5647000074386597},{"id":"https://openalex.org/keywords/guard","display_name":"Guard (computer science)","score":0.4934999942779541},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4097000062465668},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.40610000491142273},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.4027000069618225},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3564000129699707}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8873000144958496},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6313999891281128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6299999952316284},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5724999904632568},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.5647000074386597},{"id":"https://openalex.org/C141141315","wikidata":"https://www.wikidata.org/wiki/Q2379942","display_name":"Guard (computer science)","level":2,"score":0.4934999942779541},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46129998564720154},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.40610000491142273},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.3269999921321869},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3127000033855438},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.30090001225471497},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2703999876976013},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.21243","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.21243","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"doi:10.48550/arxiv.2607.21243","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.21243","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6823498010635376}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"AI-enabled":[0],"visual":[1],"perception":[2],"systems":[3],"are":[4],"increasingly":[5],"deployed":[6],"in":[7],"intelligent":[8],"transportation":[9],"infrastructure":[10],"and":[11,40,79,114,122,128,144,183],"autonomous":[12],"vehicle":[13],"related":[14,212],"applications.":[15],"However,":[16],"physically":[17],"realizable":[18],"adversarial":[19,38,90,98,107,216],"appearances":[20],"pose":[21],"a":[22,58],"significant":[23],"reliability":[24],"challenge":[25],"for":[26,70],"these":[27],"safety-critical":[28],"systems.":[29],"Adversarial":[30],"training":[31,91],"is":[32],"effective,":[33],"but":[34],"repeated":[35],"co-occurrence":[36],"between":[37],"texture":[39,50,60,67,99,168,217],"positive":[41],"person":[42,108],"instances":[43],"can":[44],"cause":[45],"detectors":[46,95,193],"to":[47,166,173],"treat":[48,66],"the":[49,71,160],"itself":[51],"as":[52,68,100],"evidence":[53,69,213],"of":[54,154,181,186],"object":[55],"presence,":[56],"forming":[57],"patch":[59],"shortcut.":[61],"The":[62,201],"detector":[63,146],"may":[64],"then":[65],"target,":[72],"causing":[73],"false":[74],"detections":[75],"on":[76,138,156,209],"texture-only":[77,118],"inputs":[78],"weakening":[80],"cross":[81],"attack":[82,126,136,152],"generalisation.":[83],"We":[84,131],"propose":[85],"InsCAT,":[86],"an":[87,101,150,178,184,220],"instance-level":[88],"contrastive":[89],"framework":[92],"that":[93,204],"prevents":[94],"from":[96,117,171,218],"using":[97],"independent":[102,221],"decision":[103,222],"cue.":[104],"SICA":[105],"aligns":[106],"features":[109,113],"with":[110,198],"matched":[111],"clean":[112],"separates":[115],"them":[116],"negatives,":[119],"while":[120,214],"ROPO":[121],"Guard":[123],"maintain":[124],"online":[125],"pressure":[127],"coordinate":[129],"training.":[130],"evaluate":[132],"eight":[133],"independently":[134],"generated":[135],"textures":[137],"rendered":[139,157],"nuScenes,":[140,158],"INRIAPerson,":[141],"printed":[142],"garments,":[143],"three":[145],"families.":[147],"InsCAT":[148],"achieves":[149],"average":[151],"AP":[153],"82.3%":[155],"exceeding":[159],"strongest":[161],"baseline":[162],"by":[163],"11.1":[164],"points.Relative":[165],"AT-Mix,":[167],"FPR":[169,185],"decreases":[170],"46.9%":[172],"7.3%.":[174],"Physical":[175],"tests":[176],"yield":[177],"F1":[179],"score":[180],"96.6%":[182],"1.8%.":[187],"Consistent":[188],"gains":[189],"across":[190,196],"separately":[191],"trained":[192],"demonstrate":[194],"applicability":[195],"architectures":[197],"direct":[199],"inference.":[200],"findings":[202],"show":[203],"robust":[205],"physical":[206],"detection":[207],"depends":[208],"preserving":[210],"target":[211],"preventing":[215],"becoming":[219],"cu":[223]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-25T00:00:00"}