{"id":"https://openalex.org/W7204185030","doi":"https://doi.org/10.48550/arxiv.2608.21841","title":"AI Watchdog: Agent Interfaces for Detecting and Defending Against Manipulative Dark Patterns in AI Conversations","display_name":"AI Watchdog: Agent Interfaces for Detecting and Defending Against Manipulative Dark Patterns in AI Conversations","publication_year":2026,"publication_date":"2026-08-22","ids":{"openalex":"https://openalex.org/W7204185030","doi":"https://doi.org/10.48550/arxiv.2608.21841"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.21841","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21841","pdf_url":"https://arxiv.org/pdf/2608.21841","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.21841","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120727116","display_name":"Rachel Poonsiriwong","orcid":"https://orcid.org/0009-0003-0759-2969","observed_orcids":["https://orcid.org/0009-0003-0759-2969"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Poonsiriwong, Rachel","raw_affiliation_strings":["Pub"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pub","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148163910","display_name":"Chayapatr","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chayapatr","raw_affiliation_strings":["Pub"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pub","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148107595","display_name":"Archiwaranguprok","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Archiwaranguprok","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049101783","display_name":"Cassie Albrecht","orcid":"https://orcid.org/0009-0002-3120-3524","observed_orcids":["https://orcid.org/0009-0002-3120-3524"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Albrecht, Constanze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098767899","display_name":"Monchai Lertsutthiwong","orcid":"https://orcid.org/0009-0002-5905-2633","observed_orcids":["https://orcid.org/0009-0002-5905-2633"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lertsutthiwong, Monchai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081457786","display_name":"Pattie Maes","orcid":"https://orcid.org/0000-0002-7722-6038","observed_orcids":["https://orcid.org/0000-0002-7722-6038","https://orcid.org/0000-0001-5175-3959"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maes, Pattie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036506156","display_name":"Pat Pataranutaporn","orcid":"https://orcid.org/0000-0002-1879-7340","observed_orcids":["https://orcid.org/0000-0002-1879-7340"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pataranutaporn, Pat","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":true,"cited_by_count":1,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.43549999594688416,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.43549999594688416,"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/T10803","display_name":"Innovative Human-Technology Interaction","score":0.3212999999523163,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11147","display_name":"Misinformation and Its Impacts","score":0.04729999974370003,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/dark-patterns","display_name":"dark patterns","score":0.9440000057220459},{"id":"https://openalex.org/keywords/conversational-ai","display_name":"conversational AI","score":0.8700000047683716},{"id":"https://openalex.org/keywords/ai-manipulation","display_name":"AI manipulation","score":0.6029999852180481},{"id":"https://openalex.org/keywords/agent-interfaces","display_name":"agent interfaces","score":0.6370000243186951},{"id":"https://openalex.org/keywords/nudging","display_name":"nudging","score":0.5730000138282776},{"id":"https://openalex.org/keywords/prebunking","display_name":"prebunking","score":0.8240000009536743},{"id":"https://openalex.org/keywords/sycophancy","display_name":"sycophancy","score":0.7229999899864197},{"id":"https://openalex.org/keywords/anthropomorphism","display_name":"anthropomorphism","score":0.8669999837875366},{"id":"https://openalex.org/keywords/sneaking","display_name":"sneaking","score":0.6710000038146973},{"id":"https://openalex.org/keywords/trust-in-ai","display_name":"trust in AI","score":0.6439999938011169},{"id":"https://openalex.org/keywords/susceptibility-to-misinformation","display_name":"misinformation susceptibility","score":0.9449999928474426},{"id":"https://openalex.org/keywords/user-awareness","display_name":"user awareness","score":0.6970000267028809},{"id":"https://openalex.org/keywords/local-inference","display_name":"local inference","score":0.5540000200271606},{"id":"https://openalex.org/keywords/user-privacy","display_name":"user privacy","score":0.6830000281333923}],"concepts":[{"id":"https://openalex.org/C2776990098","wikidata":"https://www.wikidata.org/wiki/Q13579947","display_name":"Misinformation","level":2,"score":0.7297999858856201},{"id":"https://openalex.org/C2777548347","wikidata":"https://www.wikidata.org/wiki/Q5456937","display_name":"Flagging","level":2,"score":0.7192000150680542},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.532800018787384},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.5081999897956848},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C2781460075","wikidata":"https://www.wikidata.org/wiki/Q1399332","display_name":"Compliance (psychology)","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.47850000858306885},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4584999978542328},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.383899986743927},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.35830000042915344},{"id":"https://openalex.org/C2780343955","wikidata":"https://www.wikidata.org/wiki/Q333173","display_name":"Surprise","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.33899998664855957},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C83804111","wikidata":"https://www.wikidata.org/wiki/Q1063558","display_name":"Behavioral pattern","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3102000057697296},{"id":"https://openalex.org/C61641136","wikidata":"https://www.wikidata.org/wiki/Q1107019","display_name":"Cognitive load","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2930000126361847},{"id":"https://openalex.org/C2779267917","wikidata":"https://www.wikidata.org/wiki/Q170028","display_name":"Deception","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C47385372","wikidata":"https://www.wikidata.org/wiki/Q7098943","display_name":"Optimal distinctiveness theory","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C57473165","wikidata":"https://www.wikidata.org/wiki/Q7315604","display_name":"Resistance (ecology)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.2517000138759613},{"id":"https://openalex.org/C2776990265","wikidata":"https://www.wikidata.org/wiki/Q2998101","display_name":"Cursor (databases)","level":2,"score":0.25130000710487366},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.21841","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21841","pdf_url":"https://arxiv.org/pdf/2608.21841","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.21841","doi":"https://doi.org/10.48550/arxiv.2608.21841","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.21841","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"pmh:oai:arXiv.org:2608.21841","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21841","pdf_url":"https://arxiv.org/pdf/2608.21841","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204185030.pdf","grobid_xml":"https://content.openalex.org/works/W7204185030.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1982451263","https://openalex.org/W2015762759","https://openalex.org/W2059216172","https://openalex.org/W2157337727","https://openalex.org/W2158241055","https://openalex.org/W2523153599","https://openalex.org/W2545457694","https://openalex.org/W2804733712","https://openalex.org/W2916904544","https://openalex.org/W3033023648","https://openalex.org/W3044862824","https://openalex.org/W4283168787","https://openalex.org/W4288058319","https://openalex.org/W4297830876","https://openalex.org/W4311510042","https://openalex.org/W4313294891","https://openalex.org/W4366590585","https://openalex.org/W4384302739","https://openalex.org/W4403153979","https://openalex.org/W4403746738","https://openalex.org/W4404392058","https://openalex.org/W4414434127","https://openalex.org/W4415090975","https://openalex.org/W4415110535","https://openalex.org/W4415160894","https://openalex.org/W4415195234","https://openalex.org/W4415250053","https://openalex.org/W4415695881","https://openalex.org/W4415978461","https://openalex.org/W4416235412","https://openalex.org/W4416852999","https://openalex.org/W4417076749","https://openalex.org/W4417280606","https://openalex.org/W6966798381","https://openalex.org/W7106424589","https://openalex.org/W7128476234","https://openalex.org/W7128819858","https://openalex.org/W7147686807","https://openalex.org/W7151421112"],"related_works":["https://openalex.org/W7159824377","https://openalex.org/W7134202247","https://openalex.org/W7214188125","https://openalex.org/W7220400163","https://openalex.org/W4412046620","https://openalex.org/W7203775804","https://openalex.org/W7131297773","https://openalex.org/W7168257859","https://openalex.org/W7117717332","https://openalex.org/W7078235509"],"abstract_inverted_index":{"Conversational":[0],"AI":[1,18,72,173,199],"increasingly":[2],"shapes":[3],"consequential":[4],"decisions,":[5],"yet":[6],"users":[7,43],"have":[8],"limited":[9],"support":[10],"for":[11],"recognizing":[12],"and":[13,38,41,54,96,115,180,195],"resisting":[14],"manipulation.":[15],"We":[16,70],"present":[17],"Watchdog,":[19],"a":[20,55,75,84],"browser-based":[21],"agent":[22],"interface":[23],"that":[24,106,158,188],"monitors":[25],"live":[26],"conversations,":[27],"detects":[28],"five":[29],"dark-pattern":[30],"categories,":[31],"including":[32],"sycophancy,":[33],"brand":[34],"bias,":[35],"anthropomorphization,":[36],"sneaking,":[37],"harmful":[39],"generation,":[40],"alerts":[42],"when":[44],"they":[45],"occur.":[46],"Its":[47],"open-weight":[48],"turn-level":[49],"classifier":[50],"supports":[51],"independent":[52],"deployment":[53],"path":[56],"toward":[57],"local":[58],"inference,":[59],"preserving":[60],"user":[61],"privacy":[62],"while":[63,171],"remaining":[64],"separate":[65],"from":[66,146],"the":[67,131],"conversational":[68,192],"AI.":[69],"evaluated":[71],"Watchdog":[73],"in":[74],"preregistered,":[76],"five-condition":[77],"between-subjects":[78],"experiment":[79],"(N":[80],"=":[81],"150)":[82],"comparing":[83],"no-intervention":[85],"control":[86],"with":[87,101,138,164,177],"four":[88],"configurations":[89],"varying":[90],"nudge":[91],"timing":[92],"(prebunking":[93],"vs.":[94,100],"just-in-time)":[95],"engagement":[97],"mode":[98],"(without":[99],"cognitive":[102,128],"forcing).":[103],"Results":[104],"show":[105],"participants":[107],"rarely":[108],"flagged":[109],"manipulative":[110],"turns":[111],"across":[112,122],"all":[113],"conditions,":[114],"post-task":[116],"awareness":[117],"did":[118],"not":[119,168],"differ":[120],"significantly":[121,135],"groups.":[123],"However,":[124],"just-in-time":[125],"warnings":[126],"without":[127],"forcing":[129],"were":[130],"only":[132],"intervention":[133],"to":[134,148,198],"reduce":[136],"compliance":[137,145,179],"AI-steered":[139],"recommendations":[140],"containing":[141],"dark":[142,193],"patterns,":[143],"lowering":[144],"71.7%":[147],"53.7%,":[149],"an":[150],"18":[151],"percentage-point":[152],"reduction.":[153],"Exploratory":[154],"analyses":[155],"further":[156,206],"showed":[157],"lower":[159,169,181],"misinformation":[160],"susceptibility":[161],"was":[162,175],"associated":[163,176],"greater":[165,178],"flagging":[166],"but":[167],"compliance,":[170],"higher":[172],"trust":[174],"reported":[182],"awareness.":[183],"Together,":[184],"these":[185],"findings":[186],"suggest":[187],"explicit":[189],"recognition":[190],"of":[191,208],"patterns":[194],"behavioral":[196],"resistance":[197],"steering":[200],"may":[201],"be":[202],"distinct":[203],"outcomes,":[204],"motivating":[205],"investigation":[207],"timely,":[209],"low-friction":[210],"defensive":[211],"interfaces.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-26T00:00:00"}