{"id":"https://openalex.org/W7127349965","doi":"https://doi.org/10.48550/arxiv.2602.01425","title":"One Probe Won't Catch Them All: Towards Targeted Deception Detection","display_name":"One Probe Won't Catch Them All: Towards Targeted Deception Detection","publication_year":2026,"publication_date":"2026-02-01","ids":{"openalex":"https://openalex.org/W7127349965","doi":"https://doi.org/10.48550/arxiv.2602.01425"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.01425","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.01425","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.01425","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001392251","display_name":"Vikram Natarajan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Natarajan, Vikram","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124898817","display_name":"Devina Jain","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jain, Devina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124963033","display_name":"Shivam Arora","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arora, Shivam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124888375","display_name":"Satvik Golechha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Golechha, Satvik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124931395","display_name":"Joseph Bloom","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bloom, Joseph","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":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/T12268","display_name":"Deception detection and forensic psychology","score":0.7182000279426575,"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"}},"topics":[{"id":"https://openalex.org/T12268","display_name":"Deception detection and forensic psychology","score":0.7182000279426575,"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"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.03590000048279762,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.03189999982714653,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/deception","display_name":"Deception","score":0.9185000061988831},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.7267000079154968},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.7250999808311462},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5983999967575073},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.3521000146865845},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.3089999854564667}],"concepts":[{"id":"https://openalex.org/C2779267917","wikidata":"https://www.wikidata.org/wiki/Q170028","display_name":"Deception","level":2,"score":0.9185000061988831},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.7267000079154968},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.7250999808311462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6319000124931335},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5983999967575073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4652000069618225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3977000117301941},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3952000141143799},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3050999939441681},{"id":"https://openalex.org/C112789634","wikidata":"https://www.wikidata.org/wiki/Q18207010","display_name":"False positives and false negatives","level":3,"score":0.3021000027656555},{"id":"https://openalex.org/C2776437466","wikidata":"https://www.wikidata.org/wiki/Q60920","display_name":"Lie detection","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2824000120162964},{"id":"https://openalex.org/C2780224610","wikidata":"https://www.wikidata.org/wiki/Q1530061","display_name":"Credibility","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C2989486834","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"True positive rate","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C119421448","wikidata":"https://www.wikidata.org/wiki/Q2268776","display_name":"Lying","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C79585631","wikidata":"https://www.wikidata.org/wiki/Q431498","display_name":"Confirmation bias","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2565000057220459},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.01425","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.01425","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.01425","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.01425","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,"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":null,"license_id":null,"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":0.586296558380127}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Linear":[0],"probes":[1,37,85,151],"are":[2,86],"a":[3,18,23,28,66,101,155],"promising":[4],"approach":[5],"for":[6,10],"monitoring":[7],"AI":[8],"systems":[9],"deceptive":[11,118],"behaviour.":[12],"Previous":[13],"work":[14],"has":[15],"shown":[16],"that":[17,59,114,139],"linear":[19],"classifier":[20],"trained":[21],"on":[22,51],"contrastive":[24],"instruction":[25,115],"pair":[26],"and":[27,48,92,147],"simple":[29],"dataset":[30],"can":[31],"achieve":[32],"good":[33],"performance.":[34],"However,":[35],"these":[36],"exhibit":[38],"notable":[39],"failures":[40],"even":[41],"in":[42,109],"straightforward":[43],"scenarios,":[44],"including":[45],"spurious":[46],"correlations":[47],"false":[49],"positives":[50],"non-deceptive":[52],"responses.":[53],"In":[54],"this":[55,97,135],"paper,":[56],"we":[57,137],"demonstrate":[58],"deception":[60,90,105,157],"detection":[61],"is":[62,99,107],"inherently":[63],"heterogeneous:":[64],"while":[65],"single":[67],"universal":[68,156],"probe":[69,129],"achieves":[70],"modest":[71],"improvements":[72],"(+0.032":[73],"AUC),":[74],"post-hoc":[75],"oracle":[76],"analysis":[77],"reveals":[78],"substantially":[79],"higher":[80],"potential":[81],"(+0.108":[82],"AUC)":[83],"when":[84,103],"matched":[87,150],"to":[88],"specific":[89,144],"types,":[91],"synthetic":[93],"validation":[94],"experiments":[95],"suggest":[96],"ceiling":[98],"achievable":[100],"priori":[102],"the":[104],"type":[106],"known":[108],"advance.":[110],"Our":[111],"findings":[112],"reveal":[113],"pairs":[116],"capture":[117],"intent":[119],"rather":[120,152],"than":[121,153],"content-specific":[122],"patterns,":[123],"explaining":[124],"why":[125],"prompt":[126],"choice":[127],"dominates":[128],"performance":[130],"(70.6%":[131],"of":[132],"variance).":[133],"Given":[134],"heterogeneity,":[136],"conclude":[138],"organizations":[140],"should":[141],"define":[142],"their":[143],"threat":[145],"models":[146],"deploy":[148],"appropriately":[149],"seeking":[154],"detector.":[158]},"counts_by_year":[],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2026-02-04T00:00:00"}