{"id":"https://openalex.org/W3136758972","doi":null,"title":"Adversarial Feature Stacking for Accurate and Robust Predictions.","display_name":"Adversarial Feature Stacking for Accurate and Robust Predictions.","publication_year":2021,"publication_date":"2021-03-24","ids":{"openalex":"https://openalex.org/W3136758972","mag":"3136758972"},"language":"en","primary_location":{"id":"mag:3136758972","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.13124.pdf","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,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.13124.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037705126","display_name":"Faqiang Liu","orcid":"https://orcid.org/0000-0002-2236-0539","observed_orcids":["https://orcid.org/0000-0002-2236-0539"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Faqiang Liu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2236-0539","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675943","display_name":"Rong Juan Zhao","orcid":"https://orcid.org/0000-0002-2320-0326","observed_orcids":["https://orcid.org/0000-0002-2320-0326"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong Zhao","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2320-0326","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018476895","display_name":"Luping Shi","orcid":"https://orcid.org/0000-0002-9829-2202","observed_orcids":["https://orcid.org/0000-0002-9829-2202"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luping Shi","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":"https://orcid.org/0000-0002-9829-2202","affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":1.0,"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":1.0,"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/T11424","display_name":"Security and Verification in Computing","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0,"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-robustness","display_name":"adversarial robustness","score":0.8709999918937683},{"id":"https://openalex.org/keywords/accuracy-robustness-trade-off","display_name":"robustness-accuracy trade-off","score":0.9070000052452087},{"id":"https://openalex.org/keywords/adversarial-training","display_name":"adversarial training","score":0.9300000071525574},{"id":"https://openalex.org/keywords/feature-fusion","display_name":"feature fusion","score":0.7300000190734863},{"id":"https://openalex.org/keywords/multiple-networks","display_name":"multiple networks","score":0.40299999713897705},{"id":"https://openalex.org/keywords/adaptive-attacks","display_name":"adaptive attacks","score":0.5730000138282776},{"id":"https://openalex.org/keywords/limited-training-data","display_name":"limited training data","score":0.7519999742507935},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.5669999718666077}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8649611473083496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77280592918396},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7684271335601807},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.6632430553436279},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6220208406448364},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6127340793609619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5984469652175903},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5498209595680237},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5168555378913879},{"id":"https://openalex.org/C33347731","wikidata":"https://www.wikidata.org/wiki/Q285210","display_name":"Stacking","level":2,"score":0.4818671643733978},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3765866160392761},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32450857758522034},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11287879943847656},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C46141821","wikidata":"https://www.wikidata.org/wiki/Q209402","display_name":"Nuclear magnetic resonance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3136758972","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.13124.pdf","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,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3136758972","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.13124.pdf","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,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W2174868984","https://openalex.org/W2194775991","https://openalex.org/W2395611524","https://openalex.org/W2460937040","https://openalex.org/W2503523779","https://openalex.org/W2543927648","https://openalex.org/W2607219512","https://openalex.org/W2620038827","https://openalex.org/W2626778328","https://openalex.org/W2765233338","https://openalex.org/W2765424254","https://openalex.org/W2766462876","https://openalex.org/W2774018344","https://openalex.org/W2774644650","https://openalex.org/W2786118190","https://openalex.org/W2786163515","https://openalex.org/W2787708942","https://openalex.org/W2787733970","https://openalex.org/W2803392236","https://openalex.org/W2874797877","https://openalex.org/W2897355816","https://openalex.org/W2901213450","https://openalex.org/W2912070915","https://openalex.org/W2913266441","https://openalex.org/W2919115771","https://openalex.org/W2947099774","https://openalex.org/W2962872506","https://openalex.org/W2963207607","https://openalex.org/W2963341956","https://openalex.org/W2964137095","https://openalex.org/W2964153729","https://openalex.org/W2964253222","https://openalex.org/W2970088379","https://openalex.org/W2970115835","https://openalex.org/W2991240978","https://openalex.org/W2995245581","https://openalex.org/W3006834354","https://openalex.org/W3006935033","https://openalex.org/W3007305010","https://openalex.org/W3008105014","https://openalex.org/W3009542902","https://openalex.org/W3009809968","https://openalex.org/W3030163527","https://openalex.org/W3037182574","https://openalex.org/W3092171228","https://openalex.org/W3101700548","https://openalex.org/W3103385169","https://openalex.org/W3106250896","https://openalex.org/W3120915204","https://openalex.org/W3125614726","https://openalex.org/W3204427153"],"related_works":["https://openalex.org/W4294831454","https://openalex.org/W4414825294","https://openalex.org/W7168404727","https://openalex.org/W4414129227","https://openalex.org/W4411484463","https://openalex.org/W4394627326","https://openalex.org/W3033197720","https://openalex.org/W3168933950","https://openalex.org/W7118011393","https://openalex.org/W4399526174"],"abstract_inverted_index":{"Deep":[0],"Neural":[1],"Networks":[2],"(DNNs)":[3],"have":[4,27],"achieved":[5],"remarkable":[6],"performance":[7],"on":[8,52,162,196,200],"a":[9,72,85,150,190],"variety":[10],"of":[11,108,113,179,194,229],"applications":[12],"but":[13],"are":[14,146],"extremely":[15],"vulnerable":[16],"to":[17,30,64,134,153,219],"adversarial":[18,43,211],"perturbation.":[19],"To":[20,91],"address":[21],"this":[22,93],"issue,":[23],"various":[24],"defense":[25],"methods":[26],"been":[28],"proposed":[29],"enhance":[31],"model":[32,50,102,161,188],"robustness.":[33,90],"Unfortunately,":[34],"the":[35,120,159,175,180,186,209,217,227],"most":[36],"representative":[37],"and":[38,45,68,89,115,164,198,223],"promising":[39],"methods,":[40,171],"such":[41,78],"as":[42,79],"training":[44,81,184,212,231],"its":[46],"variants,":[47],"usually":[48],"degrade":[49],"accuracy":[51,88,192],"benign":[53,191],"samples,":[54],"limiting":[55],"practical":[56],"utility.":[57],"This":[58,214],"indicates":[59],"that":[60,103],"it":[61],"is":[62],"difficult":[63],"extract":[65,135],"both":[66,221],"robust":[67,138,224],"accurate":[69,142,222],"features":[70,109,139,145],"using":[71],"single":[73],"network":[74],"under":[75,226],"certain":[76],"conditions,":[77],"limited":[80,230],"data,":[82,185],"resulting":[83],"in":[84,177],"trade-off":[86],"between":[87],"tackle":[92],"problem,":[94],"we":[95,124],"propose":[96],"an":[97],"Adversarial":[98],"Feature":[99],"Stacking":[100],"(AFS)":[101],"can":[104],"jointly":[105],"take":[106],"advantage":[107],"with":[110,130,167,202],"varied":[111],"levels":[112],"robustness":[114,207],"accuracy,":[116],"thus":[117],"significantly":[118,173],"alleviating":[119],"aforementioned":[121],"trade-off.":[122,181],"Specifically,":[123],"adopt":[125],"multiple":[126],"networks":[127],"adversarially":[128],"trained":[129],"different":[131],"perturbation":[132],"budgets":[133],"either":[136],"more":[137,141],"or":[140,204],"features.":[143],"These":[144],"then":[147],"fused":[148],"by":[149],"learnable":[151],"merger":[152],"give":[154],"final":[155],"predictions.":[156],"We":[157],"evaluate":[158],"AFS":[160,187],"CIFAR-10":[163,197],"CIFAR-100":[165,201],"datasets":[166],"strong":[168],"adaptive":[169],"attack":[170],"which":[172],"advances":[174],"state-of-the-art":[176,210],"terms":[178],"Without":[182],"extra":[183],"achieves":[189],"improvement":[193],"6%":[195],"9%":[199],"comparable":[203],"even":[205],"stronger":[206],"than":[208],"methods.":[213],"work":[215],"demonstrates":[216],"feasibility":[218],"obtain":[220],"models":[225],"circumstances":[228],"data.":[232]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-03-29T00:00:00"}