{"id":"https://openalex.org/W7165033833","doi":"https://doi.org/10.48550/arxiv.2606.17540","title":"TaFD: Threat-Aware Frequency Decoupling for Adversarial Robustness against Heterogeneous Attacks","display_name":"TaFD: Threat-Aware Frequency Decoupling for Adversarial Robustness against Heterogeneous Attacks","publication_year":2026,"publication_date":"2026-06-16","ids":{"openalex":"https://openalex.org/W7165033833","doi":"https://doi.org/10.48550/arxiv.2606.17540"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.17540","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17540","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":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.2606.17540","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066633053","display_name":"Mengda Xie","orcid":"https://orcid.org/0009-0003-3264-4871"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Mengda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121999607","display_name":"Y He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Yiling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073389511","display_name":"Meie Fang","orcid":"https://orcid.org/0000-0003-4292-8889"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Meie","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":0.9955000281333923,"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":0.9955000281333923,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.00039999998989515007,"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":0.0003000000142492354,"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/robustness","display_name":"Robustness (evolution)","score":0.6517000198364258},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5679000020027161},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5217999815940857},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.5041999816894531},{"id":"https://openalex.org/keywords/spectral-clustering","display_name":"Spectral clustering","score":0.450300008058548},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.43970000743865967},{"id":"https://openalex.org/keywords/separable-space","display_name":"Separable space","score":0.3968000113964081},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.3720000088214874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7034000158309937},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6517000198364258},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5679000020027161},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5217999815940857},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.5041999816894531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4580000042915344},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.450300008058548},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.3968000113964081},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36309999227523804},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32359999418258667},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.26510000228881836},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.17540","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17540","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":"doi:10.48550/arxiv.2606.17540","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17540","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4214023947715759,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-threat":[0],"robustness":[1,171],"remains":[2],"a":[3,74,82,101,115],"fundamental":[4],"challenge":[5],"in":[6,60],"deep":[7],"learning.":[8],"Although":[9],"joint":[10],"adversarial":[11],"training":[12],"(JAT)":[13],"is":[14],"widely":[15],"adopted,":[16],"it":[17],"suffers":[18],"from":[19],"negative":[20],"transfer":[21],"under":[22],"heterogeneous":[23,173],"threats,":[24],"particularly":[25],"between":[26],"$\\ell_p$-bounded":[27],"and":[28,41,99,123,135,149,151,159,178],"semantic":[29],"attacks.":[30],"Through":[31],"first-order":[32],"gradient":[33,39],"analysis,":[34],"we":[35,68],"formalize":[36],"this":[37,66],"as":[38,81],"incompatibility":[40],"theoretically":[42],"establish":[43],"the":[44,61,111,128,160,189],"necessity":[45],"of":[46,95],"decoupled":[47],"optimization.":[48],"We":[49,139],"further":[50],"reveal":[51],"that":[52,78,118,166],"these":[53],"conflicting":[54],"threats":[55],"exhibit":[56],"separable":[57],"spectral":[58,97,121],"characteristics":[59],"frequency":[62],"domain.":[63],"Motivated":[64],"by":[65,185],"observation,":[67],"propose":[69],"Threat-aware":[70],"Frequency":[71],"Decoupling":[72],"(TaFD),":[73],"two-stage":[75],"defense":[76],"framework":[77],"reformulates":[79],"JAT":[80,177],"frequency-domain":[83,179],"divide-and-conquer":[84],"paradigm.":[85],"TaFD":[86,113,141,167],"first":[87],"discovers":[88],"latent":[89],"threat":[90,106],"domains":[91],"via":[92],"unsupervised":[93],"clustering":[94],"attack":[96],"prototypes":[98],"trains":[100],"lightweight":[102],"classifier":[103],"for":[104],"inference-time":[105],"domain":[107],"identification.":[108],"Conditioned":[109],"on":[110,142,152],"prediction,":[112],"employs":[114],"Frequency-Conditional":[116],"Convolution":[117],"learns":[119],"threat-domain-specific":[120],"masks":[122],"routes":[124],"each":[125],"sample":[126],"to":[127],"corresponding":[129],"expert,":[130],"enforcing":[131],"structural":[132],"parameter":[133],"separation":[134],"alleviating":[136],"optimization":[137],"conflicts.":[138],"validate":[140],"three":[143],"representative":[144,154],"image-classification":[145],"benchmarks":[146],"(CIFAR-10,":[147],"CIFAR-100,":[148],"Tiny-ImageNet)":[150],"two":[153],"architectures":[155],"(the":[156],"convolutional":[157],"ResNet":[158],"hybrid-transformer":[161],"MobileViT).":[162],"Extensive":[163],"results":[164],"demonstrate":[165],"achieves":[168],"more":[169],"balanced":[170],"against":[172],"attacks":[174],"than":[175],"existing":[176],"baselines,":[180],"improving":[181],"average":[182],"robust":[183],"accuracy":[184],"approximately":[186],"11\\%":[187],"over":[188],"strongest":[190],"baseline":[191],"while":[192],"maintaining":[193],"leading":[194],"clean":[195],"accuracy.":[196]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-18T00:00:00"}