{"id":"https://openalex.org/W4417135172","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227836","title":"ProARD: Progressive Adversarial Robustness Distillation: Provide Wide Range of Robust Students","display_name":"ProARD: Progressive Adversarial Robustness Distillation: Provide Wide Range of Robust Students","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4417135172","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227836"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227836","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.07666","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101532768","display_name":"S. M. Mousavi","orcid":"https://orcid.org/0000-0003-2685-9158"},"institutions":[{"id":"https://openalex.org/I82509713","display_name":"M\u00e4lardalen University","ror":"https://ror.org/033vfbz75","country_code":"SE","type":"education","lineage":["https://openalex.org/I82509713"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Seyedhamidreza Mousavi","raw_affiliation_strings":["M&#x00E4;lardalen University,School of Innovation, Design and Engineering,Sweden"],"affiliations":[{"raw_affiliation_string":"M&#x00E4;lardalen University,School of Innovation, Design and Engineering,Sweden","institution_ids":["https://openalex.org/I82509713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027330844","display_name":"S. Mostafa Mousavi","orcid":"https://orcid.org/0000-0001-5091-5370"},"institutions":[{"id":"https://openalex.org/I82509713","display_name":"M\u00e4lardalen University","ror":"https://ror.org/033vfbz75","country_code":"SE","type":"education","lineage":["https://openalex.org/I82509713"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Seyedali Mousavi","raw_affiliation_strings":["M&#x00E4;lardalen University,School of Innovation, Design and Engineering,Sweden"],"affiliations":[{"raw_affiliation_string":"M&#x00E4;lardalen University,School of Innovation, Design and Engineering,Sweden","institution_ids":["https://openalex.org/I82509713"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063193249","display_name":"Masoud Daneshtalab","orcid":"https://orcid.org/0000-0001-6289-1521"},"institutions":[{"id":"https://openalex.org/I82509713","display_name":"M\u00e4lardalen University","ror":"https://ror.org/033vfbz75","country_code":"SE","type":"education","lineage":["https://openalex.org/I82509713"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Masoud Daneshtalab","raw_affiliation_strings":["M&#x00E4;lardalen University,School of Innovation, Design and Engineering,Sweden"],"affiliations":[{"raw_affiliation_string":"M&#x00E4;lardalen University,School of Innovation, Design and Engineering,Sweden","institution_ids":["https://openalex.org/I82509713"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101532768"],"corresponding_institution_ids":["https://openalex.org/I82509713"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20203951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9861999750137329,"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":0.9861999750137329,"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":0.0031999999191612005,"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":0.0013000000035390258,"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":0.8705999851226807},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.657800018787384},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4887999892234802},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.37720000743865967},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.3571000099182129},{"id":"https://openalex.org/keywords/dynamic-network-analysis","display_name":"Dynamic network analysis","score":0.32499998807907104},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.30730000138282776}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8705999851226807},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7228000164031982},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.657800018787384},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4887999892234802},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48190000653266907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47130000591278076},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3571000099182129},{"id":"https://openalex.org/C13540734","wikidata":"https://www.wikidata.org/wiki/Q5318996","display_name":"Dynamic network analysis","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.30309998989105225},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C32946077","wikidata":"https://www.wikidata.org/wiki/Q618079","display_name":"Network analysis","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.25429999828338623}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227836","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.07666","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.07666","pdf_url":"https://arxiv.org/pdf/2506.07666","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.07666","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.07666","pdf_url":"https://arxiv.org/pdf/2506.07666","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2535873859","https://openalex.org/W2798302089","https://openalex.org/W2963857521","https://openalex.org/W2997560666","https://openalex.org/W3021182036","https://openalex.org/W3204279503","https://openalex.org/W4214585697","https://openalex.org/W4312641744","https://openalex.org/W4320002812","https://openalex.org/W4386065434","https://openalex.org/W4396214365","https://openalex.org/W4402704571","https://openalex.org/W4402715799","https://openalex.org/W4402716028","https://openalex.org/W4402727400","https://openalex.org/W4402951695"],"related_works":[],"abstract_inverted_index":{"Adversarial":[0,78],"Robustness":[1,79],"Distillation":[2,80],"(ARD)":[3],"has":[4],"emerged":[5],"as":[6,150],"an":[7],"effective":[8],"method":[9],"to":[10,32,40,60,65,129,164,178,200,216,267,300],"enhance":[11],"the":[12,41,83,143,147,151,167,179,189,192,231,246,251,277,284,312],"robustness":[13,243,293,315],"of":[14,44,87,96,134,183,204,233,316,325],"lightweight":[15,36],"deep":[16,110],"neural":[17,111],"networks":[18,101,235,319],"against":[19],"adversarial":[20],"attacks.":[21],"Current":[22],"ARD":[23],"approaches":[24,51],"have":[25],"leveraged":[26],"a":[27,54,88,93,108,131,161,195,202,224,257,263],"large":[28],"robust":[29,35,99,220],"teacher":[30,153,169,248],"network":[31,57,90,112,145,159,170,249],"train":[33],"one":[34],"student.":[37],"However,":[38,176],"due":[39,177],"diverse":[42,94],"range":[43,95,133],"edge":[45],"devices":[46],"and":[47,69,98,123,171,219,250,275,289,292,296,314,327],"resource":[48],"constraints,":[49,63],"current":[50],"require":[52],"training":[53,86,240],"new":[55],"student":[56,100,144,174,210,234,318],"from":[58],"scratch":[59],"meet":[61],"specific":[62],"leading":[64],"substantial":[66],"computational":[67,181,285],"costs":[68],"increased":[70],"CO<inf":[71],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[72,138],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</inf>":[73],"emissions.This":[74],"paper":[75],"proposes":[76],"Progressive":[77],"(ProARD),":[81],"enabling":[82],"efficient":[84],"one-time":[85],"dynamic":[89,109,115,152,158,168,193,247],"that":[91,208,228,271,281,306],"supports":[92],"accurate":[97,218],"without":[102],"requiring":[103],"retraining.":[104],"We":[105,206,303],"first":[106],"make":[107],"based":[113,261],"on":[114,262],"layers":[116],"by":[117,287,294],"encompassing":[118],"variations":[119],"in":[120,125,212,236],"width,":[121],"depth,":[122],"expansion":[124],"each":[126,213],"design":[127],"stage":[128],"support":[130],"wide":[132],"architectures":[135,270],"(>":[136],"10<sup":[137],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">19</sup>).":[139],"Then,":[140],"we":[141,255,279],"consider":[142],"with":[146,320],"largest":[148],"size":[149,232],"network.":[154],"ProARD":[155,222,282],"trains":[156],"this":[157],"using":[160],"weight-sharing":[162],"mechanism":[163,197],"jointly":[165],"optimize":[166],"its":[172],"internal":[173],"networks.":[175],"high":[180],"cost":[182,286],"calculating":[184],"exact":[185],"gradients":[186],"for":[187],"all":[188],"students":[190],"within":[191],"network,":[194],"sampling":[196,211,226],"is":[198],"required":[199],"select":[201],"subset":[203],"students.":[205,221,253],"show":[207,280],"random":[209,301],"iteration":[214],"fails":[215],"produce":[217],"employs":[223],"progressive":[225],"strategy":[227],"gradually":[229],"reduces":[230,283],"three":[237],"steps":[238],"during":[239],"while":[241],"applying":[242],"distillation":[244],"between":[245],"selected":[252],"Finally,":[254],"leverage":[256],"multi-objective":[258],"evolutionary":[259],"algorithm":[260],"proposed":[264],"accuracy-robustness":[265,308],"predictor":[266,309],"identify":[268],"optimal":[269],"balance":[272],"accuracy,":[273],"robustness,":[274],"efficiency.Through":[276],"experiments,":[278],"60\u00d7":[288],"improves":[290],"accuracy":[291,313],"13%":[295],"14%,":[297],"respectively,":[298],"compared":[299],"sampling.":[302],"also":[304],"demonstrate":[305],"our":[307],"can":[310],"estimate":[311],"test":[317],"root":[321],"mean":[322],"squared":[323],"errors":[324],"0.0073":[326],"0.0072,":[328],"respectively.":[329]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-11-14T00:00:00"}