{"id":"https://openalex.org/W7160946951","doi":"https://doi.org/10.1007/s43681-026-01132-0","title":"The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems","display_name":"The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7160946951","doi":"https://doi.org/10.1007/s43681-026-01132-0"},"language":"en","primary_location":{"id":"doi:10.1007/s43681-026-01132-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s43681-026-01132-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s43681-026-01132-0.pdf","source":{"id":"https://openalex.org/S4210170699","display_name":"AI and Ethics","issn_l":"2730-5953","issn":["2730-5953","2730-5961"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AI and Ethics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s43681-026-01132-0.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024434748","display_name":"Gjergji Kasneci","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Gjergji Kasneci","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135954458","display_name":"Enkelejda Kasneci","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Enkelejda Kasneci","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5024434748"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8762007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.42480000853538513,"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"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.42480000853538513,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.09309999644756317,"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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.0738999992609024,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6517000198364258},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6204000115394592},{"id":"https://openalex.org/keywords/corporate-governance","display_name":"Corporate governance","score":0.6018999814987183},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5936999917030334},{"id":"https://openalex.org/keywords/legitimacy","display_name":"Legitimacy","score":0.515999972820282},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.505299985408783},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4697999954223633}],"concepts":[{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6517000198364258},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.6251999735832214},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6204000115394592},{"id":"https://openalex.org/C39389867","wikidata":"https://www.wikidata.org/wiki/Q380767","display_name":"Corporate governance","level":2,"score":0.6018999814987183},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5936999917030334},{"id":"https://openalex.org/C46295352","wikidata":"https://www.wikidata.org/wiki/Q207982","display_name":"Legitimacy","level":3,"score":0.515999972820282},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.505299985408783},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4697999954223633},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4595000147819519},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4374000132083893},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41359999775886536},{"id":"https://openalex.org/C2778221768","wikidata":"https://www.wikidata.org/wiki/Q8964474","display_name":"Risk governance","level":3,"score":0.41200000047683716},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.3222000002861023},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.31610000133514404},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3151000142097473},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.30559998750686646},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.29580000042915344},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.29499998688697815},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.28690001368522644},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C81293917","wikidata":"https://www.wikidata.org/wiki/Q4189534","display_name":"System deployment","level":3,"score":0.26649999618530273},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2776240099","wikidata":"https://www.wikidata.org/wiki/Q327018","display_name":"Interrogation","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s43681-026-01132-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s43681-026-01132-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s43681-026-01132-0.pdf","source":{"id":"https://openalex.org/S4210170699","display_name":"AI and Ethics","issn_l":"2730-5953","issn":["2730-5953","2730-5961"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AI and Ethics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s43681-026-01132-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s43681-026-01132-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s43681-026-01132-0.pdf","source":{"id":"https://openalex.org/S4210170699","display_name":"AI and Ethics","issn_l":"2730-5953","issn":["2730-5953","2730-5961"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AI and Ethics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5641456842422485,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323383","display_name":"Technische Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/02kkvpp62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160946951.pdf","grobid_xml":"https://content.openalex.org/works/W7160946951.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W1595833668","https://openalex.org/W1979004942","https://openalex.org/W2063052894","https://openalex.org/W2281090488","https://openalex.org/W2792435043","https://openalex.org/W3001807593","https://openalex.org/W3134395196","https://openalex.org/W3159250634","https://openalex.org/W4291197616","https://openalex.org/W4321472144","https://openalex.org/W4366003124","https://openalex.org/W4367628156","https://openalex.org/W4385468994","https://openalex.org/W4386249234","https://openalex.org/W4388624604","https://openalex.org/W4388717704","https://openalex.org/W4388886073","https://openalex.org/W4389519118","https://openalex.org/W4389520670","https://openalex.org/W4390430574","https://openalex.org/W4391334942","https://openalex.org/W4391555516","https://openalex.org/W4391799275","https://openalex.org/W4392678053","https://openalex.org/W4399795554","https://openalex.org/W4399992361","https://openalex.org/W4400949264","https://openalex.org/W4402386010","https://openalex.org/W4403160620","https://openalex.org/W4403537367","https://openalex.org/W4403702563","https://openalex.org/W4403707125","https://openalex.org/W4404782832","https://openalex.org/W4405267222","https://openalex.org/W4405627013","https://openalex.org/W4407423003","https://openalex.org/W4407570660","https://openalex.org/W4407690155","https://openalex.org/W4409523169","https://openalex.org/W4409767075","https://openalex.org/W4411119426","https://openalex.org/W4412203333","https://openalex.org/W4412673546","https://openalex.org/W4412889952","https://openalex.org/W4414973934","https://openalex.org/W4415230412","https://openalex.org/W4415796822","https://openalex.org/W4415800619","https://openalex.org/W4417063441","https://openalex.org/W6891874193","https://openalex.org/W6929343257","https://openalex.org/W6948008621","https://openalex.org/W6948199273","https://openalex.org/W7105670201","https://openalex.org/W7123280946","https://openalex.org/W7129369048","https://openalex.org/W7130542677"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Current":[1],"AI":[2,68,182,243],"safety":[3,64,149,244],"discourse":[4],"still":[5],"focuses":[6],"disproportionately":[7],"on":[8,191],"visible":[9],"failures,":[10],"including":[11,204],"obvious":[12],"harms,":[13],"dramatic":[14],"misuse,":[15],"and":[16,49,97,116,134,141,155,172,175,207,226,234,237],"hypothetical":[17],"catastrophic":[18],"scenarios.":[19],"That":[20],"focus":[21],"is":[22,70],"incomplete.":[23],"In":[24],"deployed":[25],"systems,":[26],"many":[27],"of":[28],"the":[29,83,88,166,188],"most":[30],"consequential":[31],"failures":[32],"are":[33,55,118],"quieter:":[34],"plausible":[35],"rather":[36,42,185],"than":[37,43,186],"spectacular,":[38],"distributed":[39],"across":[40,151],"components":[41],"localized":[44],"in":[45,66,210],"a":[46,62,75,78,101,238],"single":[47],"output,":[48],"normalized":[50],"by":[51],"workflows":[52],"before":[53],"they":[54],"recognized":[56],"as":[57],"hazards.":[58],"We":[59,99,229],"argue":[60],"that":[61],"central":[63],"challenge":[65],"modern":[67],"systems":[69,183],"increasingly":[71],"not":[72],"only":[73],"whether":[74,82,114,131,148,163,181],"model":[76,227],"emits":[77],"harmful":[79],"response,":[80],"but":[81],"broader":[84],"socio-technical":[85,250],"system":[86],"preserves":[87],"conditions":[89],"under":[90,139],"which":[91,192],"errors":[92],"remain":[93,137],"visible,":[94],"contestable,":[95],"containable,":[96],"recoverable.":[98],"propose":[100],"five-layer":[102],"framework":[103],"for":[104,241],"diagnosing":[105],"these":[106,197],"hidden":[107],"risks:":[108],"(1)":[109],"epistemic":[110],"integrity":[111,128,145,160,178],",":[112,129,146,161,179],"concerning":[113,130,147,162,180],"evidence":[115,224],"uncertainty":[117,206],"represented":[119],"honestly":[120],"enough":[121],"to":[122,168],"support":[123],"calibrated":[124],"reliance;":[125],"(2)":[126],"control":[127],"authority,":[132],"permissions,":[133],"action":[135],"boundaries":[136],"robust":[138],"attack":[140],"optimization;":[142],"(3)":[143],"temporal":[144],"holds":[150],"sessions,":[152],"memory":[153,216],"updates,":[154],"deployment":[156],"drift;":[157],"(4)":[158],"organizational":[159],"institutions":[164],"retain":[165],"capacity":[167],"audit,":[169],"assign":[170],"responsibility,":[171],"intervene":[173],"effectively;":[174],"(5)":[176],"ecosystem":[177],"preserve":[184],"erode":[187],"information":[189],"environment":[190],"future":[193],"oversight":[194],"depends.":[195],"Across":[196],"layers,":[198],"we":[199],"identify":[200],"under-recognized":[201],"risk":[202],"patterns,":[203],"overreliance,":[205],"legitimacy":[208],"laundering":[209],"retrieval,":[211],"prompt":[212],"injection,":[213],"reward":[214],"hacking,":[215],"poisoning,":[217],"evaluation":[218,248],"deception,":[219],"fictional":[220],"human":[221],"oversight,":[222],"synthetic":[223],"pollution,":[225],"collapse.":[228],"conclude":[230],"with":[231],"actionable":[232],"design":[233],"governance":[235],"recommendations":[236],"research":[239],"agenda":[240],"shifting":[242],"from":[245],"narrow":[246],"model-centric":[247],"toward":[249],"reliability.":[251]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-05-13T00:00:00"}
