{"id":"https://openalex.org/W4298054248","doi":"https://doi.org/10.48550/arxiv.2209.14053","title":"Inducing Data Amplification Using Auxiliary Datasets in Adversarial Training","display_name":"Inducing Data Amplification Using Auxiliary Datasets in Adversarial Training","publication_year":2022,"publication_date":"2022-09-27","ids":{"openalex":"https://openalex.org/W4298054248","doi":"https://doi.org/10.48550/arxiv.2209.14053"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2209.14053","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.14053","pdf_url":"https://arxiv.org/pdf/2209.14053","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.14053","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054907411","display_name":"Saehyung Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lee, Saehyung","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102822790","display_name":"Hyungyu Lee","orcid":"https://orcid.org/0000-0003-4914-1683"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Hyungyu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054907411"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.9954000115394592,"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":0.9954000115394592,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9936000108718872,"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":0.992900013923645,"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/computer-science","display_name":"Computer science","score":0.8304927349090576},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7615193128585815},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6886164546012878},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6749755144119263},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5892404913902283},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5887436866760254},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5796302556991577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5427200794219971},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4892885386943817},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4709658920764923},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4232960045337677},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08068609237670898}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8304927349090576},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7615193128585815},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6886164546012878},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6749755144119263},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5892404913902283},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5887436866760254},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5796302556991577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5427200794219971},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4892885386943817},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4709658920764923},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4232960045337677},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08068609237670898},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2209.14053","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.14053","pdf_url":"https://arxiv.org/pdf/2209.14053","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2209.14053","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2209.14053","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.14053","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.14053","pdf_url":"https://arxiv.org/pdf/2209.14053","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4298054248.pdf","grobid_xml":"https://content.openalex.org/works/W4298054248.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2129767422","https://openalex.org/W3210196349","https://openalex.org/W4214728004","https://openalex.org/W3211393740","https://openalex.org/W3208049411","https://openalex.org/W3022908591","https://openalex.org/W2950181282","https://openalex.org/W2946768379","https://openalex.org/W2963261224","https://openalex.org/W2798287483"],"abstract_inverted_index":{"Several":[0],"recent":[1],"studies":[2],"have":[3],"shown":[4],"that":[5,26,53,126],"the":[6,69,74,111,137,145,163,167],"use":[7],"of":[8,18,113,169],"extra":[9,35],"in-distribution":[10],"data":[11,36,56,99],"can":[12,82,107],"lead":[13],"to":[14,32,132,136,151],"a":[15,38,46,59,88,118,170],"high":[16],"level":[17],"adversarial":[19,49,85,158],"robustness.":[20],"However,":[21],"there":[22],"is":[23],"no":[24],"guarantee":[25],"it":[27],"will":[28],"always":[29],"be":[30,108],"possible":[31],"obtain":[33],"sufficient":[34],"for":[37,157],"selected":[39],"dataset.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,124],"propose":[45],"biased":[47],"multi-domain":[48,96],"training":[50,55,159],"(BiaMAT)":[51],"method":[52,81,147],"induces":[54],"amplification":[57,100],"on":[58,87,101],"primary":[60,75,89,143],"dataset":[61,90],"using":[62],"publicly":[63],"available":[64,180],"auxiliary":[65,77,93,141],"datasets,":[66],"without":[67],"requiring":[68],"class":[70],"distribution":[71],"match":[72],"between":[73,140],"and":[76,104,120,142,177],"datasets.":[78],"The":[79,174],"proposed":[80,146],"achieve":[83],"increased":[84],"robustness":[86],"by":[91,160],"leveraging":[92],"datasets":[94,156],"via":[95],"learning.":[97],"Specifically,":[98],"both":[102],"robust":[103],"non-robust":[105],"features":[106],"accomplished":[109],"through":[110,117,166],"application":[112,168],"BiaMAT":[114],"as":[115],"demonstrated":[116],"theoretical":[119],"empirical":[121],"analysis.":[122],"Moreover,":[123],"demonstrate":[125],"while":[127],"existing":[128],"methods":[129],"are":[130,179],"vulnerable":[131],"negative":[133],"transfer":[134],"due":[135],"distributional":[138],"discrepancy":[139,165],"data,":[144],"enables":[148],"neural":[149],"networks":[150],"flexibly":[152],"leverage":[153],"diverse":[154],"image":[155],"successfully":[161],"handling":[162],"domain":[164],"confidence-based":[171],"selection":[172],"strategy.":[173],"pre-trained":[175],"models":[176],"code":[178],"at:":[181],"\\url{https://github.com/Saehyung-Lee/BiaMAT}.":[182]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2022-10-01T00:00:00"}