{"id":"https://openalex.org/W4307010271","doi":"https://doi.org/10.48550/arxiv.2210.10485","title":"Learning Transferable Adversarial Robust Representations via Multi-view Consistency","display_name":"Learning Transferable Adversarial Robust Representations via Multi-view Consistency","publication_year":2022,"publication_date":"2022-10-19","ids":{"openalex":"https://openalex.org/W4307010271","doi":"https://doi.org/10.48550/arxiv.2210.10485"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2210.10485","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.10485","pdf_url":"https://arxiv.org/pdf/2210.10485","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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.10485","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100665021","display_name":"Minseon Kim","orcid":"https://orcid.org/0000-0003-0221-4080","observed_orcids":["https://orcid.org/0000-0003-0221-4080"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Minseon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040594821","display_name":"Hyeonjeong Ha","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ha, Hyeonjeong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lee, Dong Bok","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Dong Bok","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Hwang, Sung Ju","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hwang, Sung Ju","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":0.8529999852180481,"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":0.8529999852180481,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.14509999752044678,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.00019999999494757503,"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":0.8700000047683716},{"id":"https://openalex.org/keywords/meta-learning","display_name":"meta-learning","score":0.9509999752044678},{"id":"https://openalex.org/keywords/few-shot-learning","display_name":"few-shot learning","score":0.9129999876022339},{"id":"https://openalex.org/keywords/multi-view-consistency","display_name":"multi-view consistency","score":0.8659999966621399},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.6100000143051147},{"id":"https://openalex.org/keywords/domain-generalization","display_name":"domain generalization","score":0.777999997138977},{"id":"https://openalex.org/keywords/transferable-representations","display_name":"transferable representations","score":0.5860000252723694},{"id":"https://openalex.org/keywords/dual-encoder","display_name":"dual encoder","score":0.6880000233650208}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9465871453285217},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7788288593292236},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.655389666557312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.636245608329773},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6044716238975525},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6023028492927551},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5923080444335938},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4750288128852844},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4682299494743347},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4331837296485901},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.414837509393692},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07274290919303894},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2210.10485","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.10485","pdf_url":"https://arxiv.org/pdf/2210.10485","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2210.10485","doi":"https://doi.org/10.48550/arxiv.2210.10485","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.10485","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.10485","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.10485","pdf_url":"https://arxiv.org/pdf/2210.10485","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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3162493389","https://openalex.org/W3103876079","https://openalex.org/W3124515882","https://openalex.org/W4312430871","https://openalex.org/W7164663810","https://openalex.org/W7103188377","https://openalex.org/W4297672467","https://openalex.org/W3201166205","https://openalex.org/W3081534675","https://openalex.org/W2982070194"],"abstract_inverted_index":{"Despite":[0],"the":[1,45,67,91,94,100,107,127,130,149],"success":[2],"on":[3,12,16,144,154],"few-shot":[4,155],"learning":[5,40,83,156],"problems,":[6],"most":[7],"meta-learned":[8],"models":[9],"only":[10],"focus":[11],"achieving":[13,161],"good":[14],"performance":[15],"clean":[17],"examples":[18],"and":[19,41,63,112,139],"thus":[20],"easily":[21],"break":[22],"down":[23],"when":[24],"given":[25],"adversarially":[26],"perturbed":[27],"samples.":[28],"While":[29],"some":[30],"recent":[31],"works":[32],"have":[33],"shown":[34],"that":[35],"a":[36,48,78,115],"combination":[37],"of":[38,47,70,99,151],"adversarial":[39,51,58,118,169],"meta-learning":[42,170],"could":[43],"enhance":[44],"robustness":[46,59],"meta-learner":[49],"against":[50,167],"attacks,":[52],"they":[53],"fail":[54],"to":[55,60,120,132],"achieve":[56],"generalizable":[57],"unseen":[61,159],"domains":[62,138],"tasks,":[64],"which":[65],"is":[66],"ultimate":[68],"goal":[69],"meta-learning.":[71],"To":[72],"address":[73],"this":[74],"challenge,":[75],"we":[76,89,125,147],"propose":[77],"novel":[79,116],"meta-adversarial":[80],"multi-view":[81],"representation":[82],"framework":[84,153],"with":[85,110],"dual":[86],"encoders.":[87],"Specifically,":[88],"introduce":[90],"discrepancy":[92],"across":[93,129,137],"two":[95],"differently":[96],"augmented":[97],"samples":[98],"same":[101],"data":[102],"instance":[103],"by":[104],"first":[105],"updating":[106],"encoder":[108],"parameters":[109],"them":[111],"further":[113],"imposing":[114],"label-free":[117],"attack":[119],"maximize":[121,126],"their":[122],"discrepancy.":[123],"Then,":[124],"consistency":[128],"views":[131],"learn":[133],"transferable":[134],"robust":[135,164],"representations":[136],"tasks.":[140],"Through":[141],"experimental":[142],"validation":[143],"multiple":[145],"benchmarks,":[146],"demonstrate":[148],"effectiveness":[150],"our":[152],"tasks":[157],"from":[158],"domains,":[160],"over":[162],"10\\%":[163],"accuracy":[165],"improvements":[166],"previous":[168],"baselines.":[171]},"counts_by_year":[],"updated_date":"2026-09-27T08:07:27.782135","created_date":"2022-10-22T00:00:00"}