{"id":"https://openalex.org/W6903485619","doi":"https://doi.org/10.13016/dspace/jud6-ekt3","title":"Scalable Methods for Robust Machine Learning","display_name":"Scalable Methods for Robust Machine Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W6903485619","doi":"https://doi.org/10.13016/dspace/jud6-ekt3"},"language":"en","primary_location":{"id":"pmh:oai:drum.lib.umd.edu:1903/30872","is_oa":false,"landing_page_url":"http://hdl.handle.net/1903/30872","pdf_url":null,"source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"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":"Dissertation"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.13016/dspace/jud6-ekt3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Levine, Alexander Jacob","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Levine, Alexander Jacob","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":true,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9758999943733215,"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":0.9758999943733215,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.006500000134110451,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.002899999963119626,"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-system","display_name":"Adversarial system","score":0.6139000058174133},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5552999973297119},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5123999714851379},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5015000104904175},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4763000011444092},{"id":"https://openalex.org/keywords/adversarial-machine-learning","display_name":"Adversarial machine learning","score":0.39649999141693115}],"concepts":[{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7569000124931335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7113000154495239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6732000112533569},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6139000058174133},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5552999973297119},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5123999714851379},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5015000104904175},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4763000011444092},{"id":"https://openalex.org/C2778403875","wikidata":"https://www.wikidata.org/wiki/Q20312394","display_name":"Adversarial machine learning","level":3,"score":0.39649999141693115},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.3343000113964081},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C96865113","wikidata":"https://www.wikidata.org/wiki/Q2946816","display_name":"Certificate","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.28279998898506165},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.26440000534057617}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:drum.lib.umd.edu:1903/30872","is_oa":false,"landing_page_url":"http://hdl.handle.net/1903/30872","pdf_url":null,"source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"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":"Dissertation"},{"id":"doi:10.13016/dspace/jud6-ekt3","is_oa":true,"landing_page_url":"https://doi.org/10.13016/dspace/jud6-ekt3","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"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":"Collection"}],"best_oa_location":{"id":"doi:10.13016/dspace/jud6-ekt3","is_oa":true,"landing_page_url":"https://doi.org/10.13016/dspace/jud6-ekt3","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"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":"Collection"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,55,144,249,308,353,398],"recent":[1],"years,":[2],"machine":[3,99,125],"learning":[4,100,126,380],"systems":[5,101,127],"have":[6,141,186],"been":[7,142],"developed":[8,339],"that":[9,61,210,432],"demonstrate":[10],"remarkable":[11],"performance":[12,82,437],"on":[13,28,69,170],"many":[14],"tasks.":[15,71],"However,":[16,219],"naive":[17],"metrics":[18,286],"of":[19,25,46,49,74,83,98,110,173,197,254,287,306,311,323,356,364,438,444],"performance,":[20],"such":[21],"as":[22,36,377],"the":[23,33,37,47,81,96,108,111,158,171,179,206,262,269,394,424,436,442],"accuracy":[24],"a":[26,50,116,145,156,162,166,293,361,389,403,419],"classifier":[27,159],"test":[29],"samples":[30],"drawn":[31],"from":[32],"same":[34],"distribution":[35],"training":[38],"set,":[39],"can":[40,434],"provide":[41,224,300],"an":[42],"overly":[43],"optimistic":[44],"view":[45],"suitability":[48],"model":[51],"for":[52,149,183,213,319,340,349],"real-world":[53],"deployment.":[54],"this":[56,135,198,255,312,357,399,433],"dissertation,":[57,256,313,358],"we":[58,190,235,257,314,359,401],"develop":[59,236,296,315],"models":[60,84],"are":[62,90,103,121,128,205,211,345],"robust,":[63],"in":[64,130,153,192,251,371,382],"addition":[65,154],"to":[66,95,105,155,177,259,284,295,299,368,414,423],"performing":[67],"well":[68],"large-scale":[70,214],"One":[72],"notion":[73,363],"robustness":[75,185,302],"is":[76,165,291,375,386,446],"adversarial":[77,86,324,328,331],"robustness,":[78],"which":[79,102,164,189,241,383,392,411],"characterizes":[80],"under":[85,268],"attacks.":[87,307,336],"Adversarial":[88],"attacks":[89,114,344],"small,":[91],"often":[92],"imperceptible,":[93],"distortions":[94],"inputs":[97],"crafted":[104],"substantially":[106],"change":[107,178],"output":[109],"system.":[112],"These":[113],"represent":[115],"real":[117],"security":[118],"threat,":[119,136],"and":[120,195,276,333,342,408,430],"especially":[122],"concerning":[123],"when":[124,441],"used":[129],"safety-critical":[131],"applications.":[132],"To":[133,232],"mitigate":[134],"certifiably":[137,146],"robust":[138,147],"classification":[139,216],"techniques":[140,204,209,222,298],"developed.":[143],"classifier,":[148],"each":[150,384],"input":[151],"sample,":[152],"classification,":[157],"also":[160,346],"produces":[161],"certificate,":[163],"guaranteed":[167],"lower":[168],"bound":[169],"magnitude":[172],"any":[174],"perturbation":[175,288],"required":[176],"classification.":[180],"Existing":[181],"methods":[182,267,338],"certifiable":[184],"significant":[187],"limitations,":[188],"address":[191,233],"Parts":[193],"I":[194,253],"II":[196,310],"dissertation:":[199],"(i)":[200],"Currently,":[201],"randomized":[202,220,238,316],"smoothing":[203,221],"only":[207,225,282],"certification":[208,266],"viable":[212],"image":[215],"(i.e.":[217],"ImageNet).":[218],"generally":[223],"high-probability,":[226],"rather":[227],"than":[228],"exact,":[229],"certificate":[230],"results.":[231],"this,":[234],"deterministic":[237],"smoothing-based":[239,317],"algorithms,":[240],"produce":[242],"exact":[243,351],"certificates":[244],"with":[245],"finite":[246],"computational":[247],"costs.":[248],"particular,":[250],"Part":[252,309,354],"present":[258],"our":[260],"knowledge":[261,409,420],"first":[263],"deterministic,":[264,347],"ImageNet-scale":[265],"L_1,":[270],"L_p":[271],"(for":[272],"p":[273],"<":[274],"1),":[275],"\"L_0\"":[277],"metrics.":[278],"(ii)":[279],"Certification":[280],"results":[281],"apply":[283,415],"particular":[285],"size.":[289],"There":[290],"therefore":[292],"need":[294],"new":[297,321,369,390],"provable":[301],"against":[303],"different":[304,362],"types":[305,322],"algorithms":[318],"several":[320],"perturbation,":[325],"including":[326],"Wasserstein":[327],"attacks,":[329,332],"Patch":[330,341],"Data":[334],"Poisoning":[335,343],"The":[337],"allowing":[348],"efficient":[350],"certification.":[352],"III":[355],"consider":[360],"robustness:":[365],"test-time":[366],"adaptability":[367],"objectives":[370],"reinforcement":[372,379],"learning.":[373],"This":[374],"formalized":[376],"goal-conditioned":[378],"(GCRL),":[381],"episode":[385],"conditioned":[387],"by":[388],"\"goal,\"":[391],"determines":[393],"episode's":[395],"reward":[396],"function.":[397],"work,":[400],"explore":[402],"connection":[404],"between":[405],"off-policy":[406,439],"GCRL":[407,440],"distillation,":[410],"leads":[412],"us":[413],"Gradient-Based":[416],"Attention":[417],"Transfer,":[418],"distillation":[421],"technique,":[422],"Q-function":[425],"update.":[426],"We":[427],"show,":[428],"empirically":[429],"theoretically,":[431],"improve":[435],"space":[443],"goals":[445],"high-dimensional.":[447]},"counts_by_year":[],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}