{"id":"https://openalex.org/W7127369388","doi":"https://doi.org/10.1145/3795523","title":"Probabilistic Runtime Verification, Evaluation, and Risk Assessment of Visual Deep Learning Systems","display_name":"Probabilistic Runtime Verification, Evaluation, and Risk Assessment of Visual Deep Learning Systems","publication_year":2026,"publication_date":"2026-02-03","ids":{"openalex":"https://openalex.org/W7127369388","doi":"https://doi.org/10.1145/3795523"},"language":"en","primary_location":{"id":"doi:10.1145/3795523","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3795523","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082684945","display_name":"Birk Torpmann-Hagen","orcid":"https://orcid.org/0000-0002-9685-9906"},"institutions":[{"id":"https://openalex.org/I4210153474","display_name":"Simula Metropolitan Center for Digital Engineering","ror":"https://ror.org/04xtarr15","country_code":"NO","type":"nonprofit","lineage":["https://openalex.org/I184531372","https://openalex.org/I2799829267","https://openalex.org/I4210153474"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Birk Torpmann-Hagen","raw_affiliation_strings":["IFI, UiT: The Arctic University of Norway, Troms\u00f8, Norway and Simula Metropolitan Center for Digital  Engineering AS, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0002-9685-9906","affiliations":[{"raw_affiliation_string":"IFI, UiT: The Arctic University of Norway, Troms\u00f8, Norway and Simula Metropolitan Center for Digital  Engineering AS, Oslo, Norway","institution_ids":["https://openalex.org/I4210153474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104666701","display_name":"P\u00e5l Halvorsen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153474","display_name":"Simula Metropolitan Center for Digital Engineering","ror":"https://ror.org/04xtarr15","country_code":"NO","type":"nonprofit","lineage":["https://openalex.org/I184531372","https://openalex.org/I2799829267","https://openalex.org/I4210153474"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"P\u00e5l Halvorsen","raw_affiliation_strings":["Simula Metropolitan Center for Digital Engineering AS, Oslo, Norway and Oslo Metropolitan University, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0003-2073-7029","affiliations":[{"raw_affiliation_string":"Simula Metropolitan Center for Digital Engineering AS, Oslo, Norway and Oslo Metropolitan University, Oslo, Norway","institution_ids":["https://openalex.org/I4210153474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124910705","display_name":"Michael A. Riegler","orcid":null},"institutions":[{"id":"https://openalex.org/I2799829267","display_name":"Simula Research Laboratory","ror":"https://ror.org/00vn06n10","country_code":"NO","type":"facility","lineage":["https://openalex.org/I2799829267"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Michael A. Riegler","raw_affiliation_strings":["Simula Research Laboratory AS, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0002-3153-2064","affiliations":[{"raw_affiliation_string":"Simula Research Laboratory AS, Oslo, Norway","institution_ids":["https://openalex.org/I2799829267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086553840","display_name":"D. Johansen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095992","display_name":"Centre for Arctic Gas Hydrate, Environment and Climate","ror":"https://ror.org/00p8r6x45","country_code":"NO","type":"facility","lineage":["https://openalex.org/I4210095992","https://openalex.org/I78037679"]},{"id":"https://openalex.org/I78037679","display_name":"UiT The Arctic University of Norway","ror":"https://ror.org/00wge5k78","country_code":"NO","type":"education","lineage":["https://openalex.org/I78037679"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Dag Johansen","raw_affiliation_strings":["IFI, UiT: The Arctic University of Norway, Troms\u00f8, Norway"],"raw_orcid":"https://orcid.org/0000-0001-7067-6477","affiliations":[{"raw_affiliation_string":"IFI, UiT: The Arctic University of Norway, Troms\u00f8, Norway","institution_ids":["https://openalex.org/I78037679","https://openalex.org/I4210095992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11952522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"3","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9122999906539917,"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":0.9122999906539917,"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":0.01679999940097332,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.010700000450015068,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/deep-learning","display_name":"Deep learning","score":0.7657999992370605},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5062999725341797},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.48820000886917114},{"id":"https://openalex.org/keywords/risk-assessment","display_name":"Risk assessment","score":0.47999998927116394},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4440999925136566},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4120999872684479},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3671000003814697},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.35839998722076416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8682000041007996},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7657999992370605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6748999953269958},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6183000206947327},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5062999725341797},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.48820000886917114},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.47999998927116394},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4440999925136566},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4120999872684479},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36719998717308044},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.3102000057697296},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C73722673","wikidata":"https://www.wikidata.org/wiki/Q1082833","display_name":"Probabilistic risk assessment","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3795523","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3795523","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7402291297912598,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1914219707","https://openalex.org/W1979866640","https://openalex.org/W2021088830","https://openalex.org/W2028138594","https://openalex.org/W2054392209","https://openalex.org/W2061047185","https://openalex.org/W2076869196","https://openalex.org/W2531327146","https://openalex.org/W2616028256","https://openalex.org/W2630837129","https://openalex.org/W2811374795","https://openalex.org/W2898158860","https://openalex.org/W2949650786","https://openalex.org/W2953937638","https://openalex.org/W2969096242","https://openalex.org/W3011721937","https://openalex.org/W3016970897","https://openalex.org/W3039522238","https://openalex.org/W3081036064","https://openalex.org/W3087720408","https://openalex.org/W3090434739","https://openalex.org/W3100511085","https://openalex.org/W3104128335","https://openalex.org/W3201579356","https://openalex.org/W3214671430","https://openalex.org/W4221141292","https://openalex.org/W4226058368","https://openalex.org/W4288019212","https://openalex.org/W4288023055","https://openalex.org/W4297738480","https://openalex.org/W4312603874","https://openalex.org/W4408520247","https://openalex.org/W4409643185","https://openalex.org/W6912515347"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"achieving":[1],"excellent":[2],"performance":[3,46],"on":[4,124,161],"benchmarks,":[5],"deep":[6,65,199],"neural":[7],"networks":[8],"often":[9],"underperform":[10],"in":[11,21,33,102,203],"real-world":[12],"scenarios":[13,35],"due":[14],"to":[15,18,25,44,171],"their":[16,82],"sensitivity":[17],"minor":[19],"shifts":[20,30,76],"input":[22],"data,":[23],"referred":[24],"as":[26],"distributional":[27,75,135],"shifts.":[28],"These":[29],"are":[31,37],"common":[32],"practical":[34],"but":[36],"rarely":[38],"accounted":[39],"for":[40,57,192],"during":[41],"evaluations,":[42,142],"leading":[43],"inflated":[45],"metrics.":[47],"To":[48],"address":[49],"this":[50,108],"gap,":[51],"we":[52,110,167],"propose":[53],"a":[54,103,162,189],"novel":[55],"methodology":[56],"the":[58,72,85,156,194],"verification,":[59],"evaluation,":[60],"and":[61,114,151,183,196,211],"risk":[62,172,213],"assessment":[63,173],"of":[64,74,87,97,117,134,158,198],"learning":[66,200],"systems.":[67],"Our":[68,137],"approach":[69,123,138,160,187],"explicitly":[70],"models":[71],"incidence":[73],"at":[77],"run":[78],"time":[79],"by":[80,131,174,206],"estimating":[81],"probability":[83],"from":[84],"outputs":[86],"out-of-distribution":[88],"detectors.":[89],"We":[90,120,153],"combine":[91],"these":[92],"estimates":[93,116],"with":[94,143,177],"conditional":[95],"probabilities":[96],"network":[98,118],"correctness,":[99],"structuring":[100],"them":[101],"binary":[104],"tree.":[105],"By":[106],"traversing":[107],"tree,":[109],"can":[111],"compute":[112],"reliable":[113],"precise":[115],"accuracy.":[119],"assess":[121],"our":[122,159,169,186],"five":[125],"datasets,":[126],"simulating":[127],"deployment":[128],"conditions":[129],"characterized":[130],"different":[132],"frequencies":[133],"shift.":[136],"consistently":[139],"outperforms":[140],"conventional":[141],"accuracy":[144],"estimation":[145],"errors":[146],"typically":[147],"ranging":[148],"between":[149],"0.01":[150],"0.10.":[152],"further":[154],"showcase":[155],"potential":[157],"medical":[163],"segmentation":[164],"benchmark,":[165],"wherein":[166],"apply":[168],"methods":[170],"associating":[175],"costs":[176],"tree":[178],"nodes,":[179],"informing":[180],"cost\u2013benefit":[181],"analyses":[182],"decision-making.":[184],"Overall,":[185],"offers":[188],"robust":[190],"framework":[191],"improving":[193],"reliability":[195],"trustworthiness":[197],"systems,":[201],"particularly":[202],"safety-critical":[204],"applications,":[205],"providing":[207],"more":[208],"accurate":[209],"evaluations":[210],"actionable":[212],"assessments.":[214]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-02-04T00:00:00"}