{"id":"https://openalex.org/W6884858145","doi":"https://doi.org/10.13016/hly4-ysmn","title":"Towards Trustworthy Machine Learning Systems","display_name":"Towards Trustworthy Machine Learning Systems","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W6884858145","doi":"https://doi.org/10.13016/hly4-ysmn"},"language":"en","primary_location":{"id":"pmh:oai:drum.lib.umd.edu:1903/32698","is_oa":false,"landing_page_url":"http://hdl.handle.net/1903/32698","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/hly4-ysmn","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shu, Manli","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shu, Manli","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":0.5077000260353088,"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":0.5077000260353088,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.36149999499320984,"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":0.031599998474121094,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.9275000095367432},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6876999735832214},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6381000280380249},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.6096000075340271},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4578999876976013},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45010000467300415},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4352000057697296},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.41110000014305115}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9275000095367432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7184000015258789},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6901000142097473},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6876999735832214},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6381000280380249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.628600001335144},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.6096000075340271},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4578999876976013},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4352000057697296},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4043000042438507},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3788999915122986},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.304500013589859},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26089999079704285}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:drum.lib.umd.edu:1903/32698","is_oa":false,"landing_page_url":"http://hdl.handle.net/1903/32698","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/hly4-ysmn","is_oa":true,"landing_page_url":"https://doi.org/10.13016/hly4-ysmn","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/hly4-ysmn","is_oa":true,"landing_page_url":"https://doi.org/10.13016/hly4-ysmn","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":[{"score":0.7390302419662476,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Machine":[0],"learning":[1],"(ML)":[2],"has":[3],"achieved":[4],"rapid":[5,287],"progress":[6,288],"in":[7,87,160,301,303],"recent":[8,317],"years.":[9],"At":[10],"the":[11,14,31,94,139,142,158,161,223,286,313,320],"same":[12],"time,":[13,99,113],"growing":[15],"capability":[16],"of":[17,35,38,61,175,225,251,261,278,289,316,334],"AI/ML":[18],"also":[19,190],"raises":[20],"concerns":[21,308],"over":[22],"its":[23],"reliability":[24,73],"and":[25,33,52,70,136,154,194,247,257,306,339],"societal":[26,342],"impacts.":[27,343],"This":[28],"dissertation":[29,115],"investigates":[30],"robustness":[32],"trustworthiness":[34],"a":[36,172,201,230,268,299],"spectrum":[37],"ML":[39,81,177,182,215,244,263,273,304],"systems:":[40],"from":[41,46,53],"discriminative":[42],"to":[43,49,55,83,141,156,164,213,242],"generative":[44,314],"models,":[45,291,319],"model":[47],"training":[48],"data":[50,66,71,75,95,119,133,337],"collection,":[51],"vision":[54],"language.":[56],"It":[57],"covers":[58],"three":[59],"aspects":[60],"trustworthy":[62,176],"AI/ML:":[63],"Reliability":[64],"under":[65,74],"distribution":[67,76,96,109],"shifts,":[68],"interpretability,":[69],"security.First,":[72],"shifts":[77,110],"is":[78,101,171],"essential":[79],"for":[80,107,205,255],"models":[82,153,183,295],"be":[84],"reliably":[85],"deployed":[86],"real-world":[88],"scenarios.":[89],"Multiple":[90],"factors":[91],"can":[92],"affect":[93],"at":[97,111,276],"test":[98,112],"which":[100,179],"unknown":[102,108],"during":[103],"training.":[104],"To":[105],"account":[106],"this":[114,219,252,327],"first":[116],"studies":[117],"several":[118,249],"augmentation":[120,134],"techniques":[121],"that":[122,234],"are":[123,200,275],"inspired":[124],"by":[125,228,283],"adversarial":[126],"optimization.":[127],"We":[128],"start":[129],"with":[130],"an":[131,214,243],"image-space":[132],"solution":[135],"then":[137],"extend":[138],"idea":[140,224],"feature":[143],"representation":[144],"space.":[145],"In":[146,186,218,326],"addition,":[147,187],"we":[148,221,266,297,329],"look":[149],"into":[150,331],"multi-modal":[151],"vision-language":[152],"propose":[155],"address":[157],"limitations":[159],"textual":[162],"context":[163],"improve":[165,195],"their":[166,196,310,341],"zero-shot":[167],"generalization.":[168],"Second,":[169],"interpretability":[170,188],"desired":[173],"property":[174],"systems,":[178],"makes":[180],"black-box":[181],"more":[184,269,324],"accountable.":[185],"tools":[189],"help":[191],"practitioners":[192],"debug":[193],"models.":[197,264],"Saliency":[198],"maps":[199,227],"commonly":[202],"used":[203],"technique":[204],"visualizing":[206],"how":[207,237],"much":[208,238],"each":[209,239],"input":[210],"part":[211],"contributes":[212,241],"model's":[216,245],"output.":[217],"dissertation,":[220,328],"broaden":[222],"saliency":[226,232,253],"proposing":[229],"parameter-space":[231],"method":[233],"helps":[235],"identify":[236],"sub-model":[240],"output":[246],"discuss":[248,340],"applications":[250],"tool":[254],"identifying":[256],"correcting":[258],"failure":[259],"modes":[260],"off-the-shelf":[262],"Lastly,":[265],"study":[267],"adverse":[270],"scenario":[271],"where":[272],"systems":[274],"risk":[277],"being":[279],"attacked":[280],"or":[281],"compromised":[282],"adversaries.":[284],"With":[285,312],"foundation":[290],"especially":[292],"large":[293,318],"language":[294],"(LLMs),":[296],"see":[298],"spike":[300],"interest":[302],"safety":[305],"ethical":[307],"around":[309],"applications.":[311],"ability":[315],"potential":[321],"misuse":[322],"becomes":[323],"detrimental.":[325],"delve":[330],"possible":[332],"exploitations":[333],"LLMs":[335],"via":[336],"tampering":[338]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}