{"id":"https://openalex.org/W4404404089","doi":"https://doi.org/10.48550/arxiv.2411.02871","title":"Enhancing Adversarial Robustness via Uncertainty-Aware Distributional Adversarial Training","display_name":"Enhancing Adversarial Robustness via Uncertainty-Aware Distributional Adversarial Training","publication_year":2024,"publication_date":"2024-11-05","ids":{"openalex":"https://openalex.org/W4404404089","doi":"https://doi.org/10.48550/arxiv.2411.02871"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2411.02871","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.02871","pdf_url":"https://arxiv.org/pdf/2411.02871","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/2411.02871","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013743092","display_name":"Junhao Dong","orcid":"https://orcid.org/0000-0002-9150-3388"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dong, Junhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048340011","display_name":"Xinghua Qu","orcid":"https://orcid.org/0000-0001-8072-2019"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qu, Xinghua","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111364915","display_name":"Z. Jane Wang","orcid":"https://orcid.org/0009-0008-6486-0831"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Z. Jane","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068243197","display_name":"Yew-Soon Ong","orcid":"https://orcid.org/0000-0002-4480-169X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ong, Yew-Soon","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013743092"],"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9904999732971191,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9819999933242798,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.9699447751045227},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.791593074798584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6165744662284851},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5679510831832886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5157483220100403},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41595911979675293},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4094878137111664},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3607243299484253},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07305565476417542}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9699447751045227},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.791593074798584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6165744662284851},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5679510831832886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5157483220100403},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41595911979675293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4094878137111664},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3607243299484253},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07305565476417542},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/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:2411.02871","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.02871","pdf_url":"https://arxiv.org/pdf/2411.02871","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.2411.02871","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.02871","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:2411.02871","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.02871","pdf_url":"https://arxiv.org/pdf/2411.02871","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":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404404089.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W4394050964","https://openalex.org/W3211393740","https://openalex.org/W3208049411","https://openalex.org/W3022908591","https://openalex.org/W4285706568","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Despite":[0],"remarkable":[1],"achievements":[2],"in":[3,87,112],"deep":[4],"learning":[5],"across":[6,218],"various":[7,223],"domains,":[8],"its":[9,74,138],"inherent":[10],"vulnerability":[11],"to":[12,50,60,73,101,160,175],"adversarial":[13,45,75,81,106,121,135,179,183,195,232],"examples":[14,82,136,177],"still":[15],"remains":[16],"a":[17,64,117,186],"critical":[18],"concern":[19],"for":[20,35],"practical":[21],"deployment.":[22],"Adversarial":[23],"training":[24,46,122,184],"has":[25],"emerged":[26],"as":[27],"one":[28],"of":[29,105,134,145,149],"the":[30,88,92,103,131,143,147,152,167,172,192],"most":[31],"effective":[32],"defensive":[33],"techniques":[34],"improving":[36],"model":[37],"robustness":[38,233],"against":[39,54],"such":[40],"malicious":[41],"inputs.":[42],"However,":[43],"existing":[44],"schemes":[47],"often":[48],"lead":[49],"limited":[51],"generalization":[52],"ability":[53],"underlying":[55],"adversaries":[56,159],"with":[57,142],"diversity":[58,148],"due":[59],"their":[61],"overreliance":[62],"on":[63,171],"point-by-point":[65],"augmentation":[66],"strategy":[67],"by":[68,128,157],"mapping":[69],"each":[70],"clean":[71,162,176,193],"example":[72],"counterpart":[76],"during":[77,178],"training.":[78],"In":[79],"addition,":[80],"can":[83],"induce":[84],"significant":[85],"disruptions":[86],"statistical":[89,132,173],"information":[90,133],"w.r.t.":[91],"target":[93],"model,":[94],"thereby":[95,181],"introducing":[96,213],"substantial":[97],"uncertainty":[98,140],"and":[99,137,194,222,234],"challenges":[100],"modeling":[102,127],"distribution":[104],"examples.":[107],"To":[108],"circumvent":[109],"these":[110,210],"issues,":[111],"this":[113],"paper,":[114],"we":[115,164,198],"propose":[116],"novel":[118],"uncertainty-aware":[119],"distributional":[120],"method,":[123],"which":[124],"enforces":[125],"adversary":[126],"leveraging":[129],"both":[130],"corresponding":[139],"estimation,":[141],"goal":[144],"augmenting":[146],"adversaries.":[150],"Considering":[151],"potentially":[153],"negative":[154],"impact":[155],"induced":[156],"aligning":[158],"misclassified":[161],"examples,":[163],"also":[165],"refine":[166],"alignment":[168,203],"reference":[169],"based":[170],"proximity":[174],"training,":[180],"reframing":[182],"within":[185],"distribution-to-distribution":[187],"matching":[188,206],"framework":[189],"interacted":[190],"between":[191,209],"domains.":[196],"Furthermore,":[197],"design":[199],"an":[200],"introspective":[201],"gradient":[202],"approach":[204,229],"via":[205],"input":[207],"gradients":[208],"domains":[211],"without":[212],"external":[214],"models.":[215],"Extensive":[216],"experiments":[217],"four":[219],"benchmark":[220],"datasets":[221],"network":[224],"architectures":[225],"demonstrate":[226],"that":[227],"our":[228],"achieves":[230],"state-of-the-art":[231],"maintains":[235],"natural":[236],"performance.":[237]},"counts_by_year":[],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2024-11-16T00:00:00"}