{"id":"https://openalex.org/W4411624618","doi":"https://doi.org/10.1145/3703323.3703338","title":"Probabilistic Trust Intervals for Out of Distribution Detection","display_name":"Probabilistic Trust Intervals for Out of Distribution Detection","publication_year":2024,"publication_date":"2024-12-18","ids":{"openalex":"https://openalex.org/W4411624618","doi":"https://doi.org/10.1145/3703323.3703338"},"language":"en","primary_location":{"id":"doi:10.1145/3703323.3703338","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3703323.3703338","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3703323.3703338","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Data Science and Management of Data (12th ACM IKDD CODS and 30th COMAD)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3703323.3703338","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111223766","display_name":"Gagandeep Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098317","display_name":"Quansight (United States)","ror":"https://ror.org/00zeq0353","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gagandeep Singh","raw_affiliation_strings":["Quansight, Austin, USA"],"affiliations":[{"raw_affiliation_string":"Quansight, Austin, USA","institution_ids":["https://openalex.org/I4210098317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101558988","display_name":"Ishan Mishra","orcid":"https://orcid.org/0009-0001-6314-5536"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ishan Mishra","raw_affiliation_strings":["Indian Institute of Technology, Jodhpur, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Jodhpur, India","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030974286","display_name":"Deepak Mishra","orcid":"https://orcid.org/0000-0002-4078-9400"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Deepak Mishra","raw_affiliation_strings":["Indian Institute of Technology, Jodhpur, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Jodhpur, India","institution_ids":["https://openalex.org/I154549908"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111223766"],"corresponding_institution_ids":["https://openalex.org/I4210098317"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28184578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"93","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9986000061035156,"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":0.9986000061035156,"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.9882000088691711,"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"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9772999882698059,"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.6418039202690125},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6171780824661255},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.36253756284713745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31095588207244873},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2060643434524536}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6418039202690125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6171780824661255},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.36253756284713745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31095588207244873},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2060643434524536}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3703323.3703338","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3703323.3703338","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3703323.3703338","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Data Science and Management of Data (12th ACM IKDD CODS and 30th COMAD)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3703323.3703338","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3703323.3703338","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3703323.3703338","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Data Science and Management of Data (12th ACM IKDD CODS and 30th COMAD)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411624618.pdf","grobid_xml":"https://content.openalex.org/works/W4411624618.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1932198206","https://openalex.org/W1965555277","https://openalex.org/W2012041290","https://openalex.org/W2014384147","https://openalex.org/W2084840427","https://openalex.org/W2194775991","https://openalex.org/W2604272474","https://openalex.org/W2963446712","https://openalex.org/W2970121940","https://openalex.org/W2990064013","https://openalex.org/W2990138404"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"ability":[1],"of":[2,24,70,174,197,236],"a":[3,78,129,192],"deep":[4],"learning":[5],"network":[6,103,179],"to":[7,57,83,131,206],"distinguish":[8],"between":[9,226],"in-distribution":[10,107],"(ID)":[11],"and":[12,22,49,116,135,169,215,228,242],"out-of-distribution":[13],"(OOD)":[14],"inputs":[15],"is":[16],"crucial":[17],"for":[18,101,124],"ensuring":[19],"the":[20,117,186,210,234],"reliability":[21],"trustworthiness":[23],"AI":[25],"systems.":[26],"Existing":[27],"OOD":[28,59,71,85,125,151,158,248],"detection":[29,43,86],"methods":[30,53,148],"often":[31],"involve":[32],"complex":[33],"architectural":[34],"innovations,":[35],"such":[36,218],"as":[37,219],"ensemble":[38],"models,":[39],"which,":[40],"while":[41],"enhancing":[42],"accuracy,":[44],"significantly":[45,144],"increase":[46],"model":[47],"complexity":[48],"training":[50],"time.":[51],"Other":[52],"utilize":[54],"surrogate":[55,157],"samples":[56,249],"simulate":[58],"inputs,":[60,244],"but":[61],"these":[62],"may":[63],"not":[64],"generalize":[65],"well":[66],"across":[67,149,176],"different":[68],"types":[69],"data.":[72,108],"In":[73],"this":[74,133],"paper,":[75],"we":[76],"propose":[77,128],"straightforward":[79],"yet":[80],"novel":[81],"technique":[82],"enhance":[84],"in":[87,239],"pre-trained":[88],"networks":[89],"without":[90,153,246],"altering":[91],"its":[92,137],"original":[93],"parameters.":[94],"Our":[95,142],"approach":[96,163,238],"defines":[97],"probabilistic":[98],"trust":[99],"intervals":[100],"each":[102],"weight,":[104],"determined":[105],"using":[106],"During":[109],"inference,":[110],"additional":[111],"weight":[112],"values":[113],"are":[114,122],"sampled,":[115],"resulting":[118],"disagreements":[119],"among":[120],"outputs":[121],"utilized":[123],"detection.":[126],"We":[127,160],"metric":[130],"quantify":[132],"disagreement":[134],"validate":[136],"effectiveness":[138],"with":[139],"empirical":[140],"evidence.":[141],"method":[143,190,223],"outperforms":[145],"various":[146,177],"baseline":[147],"multiple":[150],"datasets":[152,217],"requiring":[154,247],"actual":[155],"or":[156],"samples.":[159],"evaluate":[161],"our":[162,189,221,237],"on":[164],"MNIST,":[165],"Fashion-MNIST,":[166],"CIFAR-10,":[167],"CIFAR-100":[168],"CIFAR-10-C":[170],"(a":[171],"corruption-augmented":[172],"version":[173],"CIFAR-10),":[175],"neural":[178],"architectures":[180],"(e.g.,":[181],"VGG-16,":[182],"ResNet-20,":[183],"DenseNet-100).":[184],"On":[185,213],"MNIST-FashionMNIST":[187],"setup,":[188],"achieves":[191],"False":[193],"Positive":[194,202],"Rate":[195,203],"(FPR)":[196],"12.46%":[198],"at":[199],"95%":[200],"True":[201],"(TPR),":[204],"compared":[205],"27.09%":[207],"achieved":[208],"by":[209],"best":[211],"baseline.":[212],"adversarial":[214,243],"corrupted":[216,241],"CIFAR-10-C,":[220],"proposed":[222],"easily":[224],"differentiate":[225],"clean":[227],"noisy":[229],"inputs.":[230],"These":[231],"results":[232],"demonstrate":[233],"robustness":[235],"identifying":[240],"all":[245],"during":[250],"training.":[251]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}