{"id":"https://openalex.org/W7225638830","doi":"https://doi.org/10.5281/zenodo.24081591","title":"Covert Informants as an AI Control Protocol: Pilot Evidence and a Planned Test of Perceived Oversight","display_name":"Covert Informants as an AI Control Protocol: Pilot Evidence and a Planned Test of Perceived Oversight","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225638830","doi":"https://doi.org/10.5281/zenodo.24081591"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24081591","doi":"https://doi.org/10.5281/zenodo.24081591","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24081591","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24081591","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161332871","display_name":"Somay Kousis","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kousis, Somay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5161332871"],"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":false,"primary_topic":{"id":"https://openalex.org/T10927","display_name":"Access Control and Trust","score":0.2653999924659729,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10927","display_name":"Access Control and Trust","score":0.2653999924659729,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.16599999368190765,"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":0.11599999666213989,"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/broker-agents","display_name":"broker agents","score":0.5460000038146973},{"id":"https://openalex.org/keywords/ai-safety","display_name":"AI safety","score":0.4620000123977661},{"id":"https://openalex.org/keywords/audit-thresholds","display_name":"audit thresholds","score":0.5059999823570251}],"concepts":[{"id":"https://openalex.org/C2779338814","wikidata":"https://www.wikidata.org/wiki/Q5179285","display_name":"Covert","level":2,"score":0.7957000136375427},{"id":"https://openalex.org/C2777363581","wikidata":"https://www.wikidata.org/wiki/Q15098235","display_name":"Harm","level":2,"score":0.7170000076293945},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.7110000252723694},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.6297000050544739},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.546999990940094},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.534600019454956},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4887999892234802},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.459199994802475},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4578000009059906},{"id":"https://openalex.org/C59577422","wikidata":"https://www.wikidata.org/wiki/Q10265143","display_name":"False accusation","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.42100000381469727},{"id":"https://openalex.org/C49630185","wikidata":"https://www.wikidata.org/wiki/Q6980675","display_name":"Natural experiment","level":2,"score":0.4032000005245209},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3953999876976013},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.33469998836517334},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.2603999972343445}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5281/zenodo.24081591","doi":"https://doi.org/10.5281/zenodo.24081591","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24081591","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.24081592","doi":"https://doi.org/10.5281/zenodo.24081592","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24081592","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.24087791","doi":"https://doi.org/10.5281/zenodo.24087791","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24087791","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24081591","doi":"https://doi.org/10.5281/zenodo.24081591","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24081591","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions","score":0.8999999761581421}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7164353457","https://openalex.org/W7164171296","https://openalex.org/W7151318516","https://openalex.org/W4417001508","https://openalex.org/W7213617131","https://openalex.org/W7170061974","https://openalex.org/W7222606078","https://openalex.org/W7104293242","https://openalex.org/W7128685405","https://openalex.org/W7117705254"],"abstract_inverted_index":{"AI":[0],"control":[1],"protocols":[2],"defend":[3],"against":[4],"an":[5,34,176],"untrusted":[6,47],"agent":[7,22,44,48,196],"with":[8,101,133],"a":[9,14,29,42,65,75,94,118,160,201,214],"weaker":[10],"trusted":[11,80],"monitor":[12],"and":[13,18,54,83,137,174,203,225,232],"small":[15],"audit":[16,77,223],"budget,":[17],"usually":[19],"assume":[20],"the":[21,32,46,55,60,91,105,109,112,115,124,134,138,157,180,190,195,211,222,227],"knows":[23],"it":[24,198],"is":[25,39,62,117,159,199],"watched.":[26],"We":[27,68,218],"study":[28],"covert":[30,36],"informant:":[31],"capability":[33],"agent's":[35],"objective":[37],"needs":[38],"moved":[40],"to":[41,152],"broker":[43,125],"that":[45,197,204],"must":[49],"instruct":[50],"in":[51,200],"natural":[52],"language,":[53],"broker,":[56],"secretly":[57],"part":[58],"of":[59,86,96,111,140,150,154],"defence,":[61],"presented":[63],"under":[64,171],"cover":[66,103,183],"identity.":[67],"ask":[69],"whether":[70],"this":[71],"raises":[72],"safety":[73],"at":[74],"fixed":[76],"budget":[78],"over":[79,163],"monitoring":[81],"alone,":[82],"how":[84],"much":[85],"any":[87],"gain":[88],"depends":[89,107],"on":[90,99,108],"cover.":[92],"In":[93],"pilot":[95],"108":[97],"episodes":[98],"SHADE-Arena":[100],"seven":[102],"conditions,":[104],"answer":[106],"shape":[110],"harm.":[113],"When":[114,156],"harm":[116,158],"single":[119],"payment,":[120],"routing":[121],"work":[122],"through":[123],"lowered":[126],"honest":[127,145],"suspicion":[128],"by":[129],"about":[130],"ten":[131],"points":[132],"same":[135],"monitor,":[136,212],"share":[139],"attacks":[141],"scoring":[142],"above":[143],"every":[144,167],"episode":[146],"rose":[147],"from":[148,210],"0":[149],"5":[151],"12":[153],"15.":[155],"pattern":[161],"spread":[162],"34":[164],"legitimate":[165],"bookings,":[166],"request":[168],"looked":[169],"benign":[170],"both":[172],"protocols,":[173],"only":[175],"aggregate":[177],"tally":[178],"caught":[179],"attacks.":[181],"The":[182],"question":[184],"could":[185],"not":[186],"yet":[187],"be":[188],"tested:":[189],"stock":[191],"attack":[192],"prompt":[193],"tells":[194],"test":[202],"its":[205],"tool":[206],"arguments":[207],"are":[208],"hidden":[209],"which":[213],"disclosed":[215],"informant":[216],"contradicts.":[217],"report":[219],"what":[220],"set":[221],"threshold":[224],"describe":[226],"planned":[228],"main":[229],"study.":[230],"Code":[231],"data:":[233],"https://github.com/Somay-kousis/Perceived-Oversight":[234]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}
