{"id":"https://openalex.org/W7131389613","doi":"https://doi.org/10.1109/icdm65498.2025.00141","title":"FAP: A Foveation-Inspired Adversarial Purification Pipeline for Enhancing Robustness in Mammography Classification","display_name":"FAP: A Foveation-Inspired Adversarial Purification Pipeline for Enhancing Robustness in Mammography Classification","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7131389613","doi":"https://doi.org/10.1109/icdm65498.2025.00141"},"language":null,"primary_location":{"id":"doi:10.1109/icdm65498.2025.00141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm65498.2025.00141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining (ICDM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126801805","display_name":"Ghazal Lalooha","orcid":null},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Ghazal Lalooha","raw_affiliation_strings":["School of Computing, Macquarie University,Sydney,NSW,Australia,2109"],"affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University,Sydney,NSW,Australia,2109","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124642737","display_name":"Wenjie Ruan","orcid":null},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wenjie Ruan","raw_affiliation_strings":["School of Computing, Macquarie University,Sydney,NSW,Australia,2109"],"affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University,Sydney,NSW,Australia,2109","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054873024","display_name":"Venus Haghighi","orcid":"https://orcid.org/0000-0002-5036-8984"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Venus Haghighi","raw_affiliation_strings":["School of Computing, Macquarie University,Sydney,NSW,Australia,2109"],"affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University,Sydney,NSW,Australia,2109","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126842592","display_name":"Xinshu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xinshu Li","raw_affiliation_strings":["School of Computing, Macquarie University,Sydney,NSW,Australia,2109"],"affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University,Sydney,NSW,Australia,2109","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126807241","display_name":"Quan Z. Sheng","orcid":null},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Quan Z. Sheng","raw_affiliation_strings":["School of Computing, Macquarie University,Sydney,NSW,Australia,2109"],"affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University,Sydney,NSW,Australia,2109","institution_ids":["https://openalex.org/I99043593"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5126801805"],"corresponding_institution_ids":["https://openalex.org/I99043593"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85592872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1320","last_page":"1329"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.29249998927116394,"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/T10862","display_name":"AI in cancer detection","score":0.29249998927116394,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.26840001344680786,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.10369999706745148,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7074000239372253},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6155999898910522},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5860999822616577},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4984999895095825},{"id":"https://openalex.org/keywords/mammography","display_name":"Mammography","score":0.4684999883174896},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.41260001063346863},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40220001339912415},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.3691999912261963},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.33230000734329224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178000211715698},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7074000239372253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7049000263214111},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6155999898910522},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5860999822616577},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4984999895095825},{"id":"https://openalex.org/C2780472235","wikidata":"https://www.wikidata.org/wiki/Q324634","display_name":"Mammography","level":4,"score":0.4684999883174896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4392000138759613},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4016000032424927},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.3691999912261963},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C2781281974","wikidata":"https://www.wikidata.org/wiki/Q324634","display_name":"Digital mammography","level":5,"score":0.3319999873638153},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2741999924182892},{"id":"https://openalex.org/C3309909","wikidata":"https://www.wikidata.org/wiki/Q864155","display_name":"Binary decision diagram","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C2910710802","wikidata":"https://www.wikidata.org/wiki/Q17011492","display_name":"Screening mammography","level":5,"score":0.260699987411499},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25850000977516174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdm65498.2025.00141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm65498.2025.00141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining (ICDM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1162227652","https://openalex.org/W3027789868","https://openalex.org/W3163711566","https://openalex.org/W3170429638","https://openalex.org/W3182906273","https://openalex.org/W4211031152","https://openalex.org/W4220851686","https://openalex.org/W4224215750","https://openalex.org/W4290033826","https://openalex.org/W4296437452","https://openalex.org/W4309334449","https://openalex.org/W4361275400","https://openalex.org/W4387745643","https://openalex.org/W4389584466","https://openalex.org/W4389610680","https://openalex.org/W4390030278","https://openalex.org/W4390738800","https://openalex.org/W4390810644","https://openalex.org/W4392460428","https://openalex.org/W4392888267","https://openalex.org/W4393871298","https://openalex.org/W4394840004","https://openalex.org/W4394908725","https://openalex.org/W4396532796","https://openalex.org/W4399069255","https://openalex.org/W4399487388","https://openalex.org/W4400126525","https://openalex.org/W4400315070","https://openalex.org/W4400409616","https://openalex.org/W4400583883","https://openalex.org/W4401942562","https://openalex.org/W4403655897","https://openalex.org/W4403827001","https://openalex.org/W4403899408","https://openalex.org/W4407449584","https://openalex.org/W4407831796","https://openalex.org/W4407831898","https://openalex.org/W4410512137","https://openalex.org/W4411799315"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"learning":[1],"models":[2],"for":[3,204],"medical":[4,208],"image":[5],"analysis":[6],"demonstrate":[7],"remarkable":[8],"diagnostic":[9,98],"accuracy":[10,170],"but":[11],"remain":[12],"highly":[13],"vulnerable":[14],"to":[15,78,133],"adversarial":[16,125,205],"perturbations.":[17],"To":[18],"address":[19],"this":[20],"challenge,":[21],"we":[22],"introduce":[23],"Foveated":[24],"Adversarial":[25],"Purification":[26],"(FAP),":[27],"a":[28,147,197],"biologically":[29],"inspired":[30],"preprocessing":[31,112],"pipeline":[32],"that":[33,111],"integrates":[34],"three":[35,160],"core":[36],"innovations.":[37],"First,":[38],"FAP":[39,83,122,163,195],"employs":[40],"eccentricity-adaptive":[41],"separable":[42],"Gaussian":[43],"blurring,":[44],"where":[45,127],"kernel":[46],"size":[47],"dynamically":[48],"adjusts":[49],"with":[50,88,96,105,114,191],"lesion":[51,138],"morphology.":[52],"This":[53,100,136],"approach":[54],"mimics":[55],"the":[56,142],"human":[57],"fovea's":[58],"acuity":[59],"gradient,":[60],"preserves":[61,137],"high-frequency":[62],"details":[63],"around":[64],"lesions":[65],"while":[66,140],"suppressing":[67],"peripheral":[68],"noise,":[69],"and":[70,180,200],"reduces":[71],"GPU":[72],"memory":[73],"usage":[74],"by":[75],"40%":[76],"compared":[77],"conventional":[79],"2D":[80],"filtering.":[81],"Second,":[82],"introduces":[84],"gradient-guided":[85],"fixation":[86],"sampling":[87],"sigmoid-clustered":[89],"probability,":[90],"which":[91],"prioritizes":[92],"lesion-dense":[93],"regions":[94,107],"consistent":[95],"radiologists'":[97],"scanpaths.":[99],"mechanism":[101],"achieves":[102,164],"82%":[103],"overlap":[104],"radiologist-annotated":[106],"of":[108,153],"interest,":[109],"ensuring":[110],"aligns":[113],"clinical":[115],"saliency":[116],"rather":[117],"than":[118],"arbitrary":[119],"regions.":[120,135],"Third,":[121],"implements":[123],"lesion-aware":[124],"training,":[126],"binary":[128],"spatial":[129],"masks":[130],"confine":[131],"perturbations":[132],"non-diagnostic":[134],"fidelity":[139],"hardening":[141],"classifier":[143],"against":[144],"attacks,":[145],"yielding":[146],"certified":[148],"\u2113<inf":[149],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[150,218,220],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</inf>":[151],"radius":[152],"1.12,":[154],"exceeding":[155],"prior":[156],"defenses.":[157],"Evaluated":[158],"across":[159],"mammography":[161],"datasets,":[162],"substantial":[165],"robustness":[166,190],"improvements:":[167],"+20.03%":[168],"absolute":[169],"on":[171,176,184],"CMMD":[172],"(coarse":[173],"tumors),":[174],"+16.39%":[175],"BREAST":[177],"(mixed":[178],"lesions),":[179],"maintains":[181],"baseline":[182],"performance":[183],"CBIS-DDSM":[185],"(microcalcifications).":[186],"By":[187],"aligning":[188],"computational":[189],"biological":[192],"vision":[193],"strategies,":[194],"establishes":[196],"clinically":[198],"interpretable":[199],"computationally":[201],"efficient":[202],"framework":[203],"defense":[206],"in":[207,214],"imaging.":[209],"The":[210],"implementation":[211],"is":[212],"released":[213],"our":[215],"GitHub":[216],"repository<sup":[217],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[219],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>https://github.com/ghazallalooha/FAP.":[221]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-02-26T00:00:00"}