{"id":"https://openalex.org/W7125978972","doi":"https://doi.org/10.1109/access.2026.3658373","title":"Learning What They Pretend to Think: Adversarial ToM for Safety-Critical Driving Policies","display_name":"Learning What They Pretend to Think: Adversarial ToM for Safety-Critical Driving Policies","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7125978972","doi":"https://doi.org/10.1109/access.2026.3658373"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3658373","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3658373","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3658373","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124144424","display_name":"Houhuang Bi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114245","display_name":"Anhui Business College","ror":"https://ror.org/02d0cgn19","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210114245"]},{"id":"https://openalex.org/I4210147760","display_name":"Wuhu Institute of Technology","ror":"https://ror.org/055hnk386","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210147760"]},{"id":"https://openalex.org/I70908550","display_name":"Anhui Polytechnic University","ror":"https://ror.org/041sj0284","country_code":"CN","type":"education","lineage":["https://openalex.org/I70908550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houhuang Bi","raw_affiliation_strings":["Wuhu Vocational Technical University, Wuhu, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhu Vocational Technical University, Wuhu, Anhui, China","institution_ids":["https://openalex.org/I70908550","https://openalex.org/I4210147760","https://openalex.org/I4210114245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110005584","display_name":"Jun Huang","orcid":"https://orcid.org/0009-0006-8549-4098"},"institutions":[{"id":"https://openalex.org/I4210114245","display_name":"Anhui Business College","ror":"https://ror.org/02d0cgn19","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210114245"]},{"id":"https://openalex.org/I4210147760","display_name":"Wuhu Institute of Technology","ror":"https://ror.org/055hnk386","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210147760"]},{"id":"https://openalex.org/I70908550","display_name":"Anhui Polytechnic University","ror":"https://ror.org/041sj0284","country_code":"CN","type":"education","lineage":["https://openalex.org/I70908550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Huang","raw_affiliation_strings":["Wuhu Vocational Technical University, Wuhu, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0006-8549-4098","affiliations":[{"raw_affiliation_string":"Wuhu Vocational Technical University, Wuhu, Anhui, China","institution_ids":["https://openalex.org/I70908550","https://openalex.org/I4210147760","https://openalex.org/I4210114245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124112602","display_name":"Yichen Han","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichen Han","raw_affiliation_strings":["South China Normal University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0003-3688-6296","affiliations":[{"raw_affiliation_string":"South China Normal University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124098183","display_name":"Zeng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeng Zhang","raw_affiliation_strings":["South China Normal University, Guangzhou, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Normal University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I187400657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12001116,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"15928","last_page":"15944"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.4620000123977661,"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":0.4620000123977661,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.3781000077724457,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.03959999978542328,"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/adversarial-system","display_name":"Adversarial system","score":0.9422000050544739},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7592999935150146},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6410999894142151},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5299999713897705},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.459199994802475},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.451200008392334},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.4120999872684479},{"id":"https://openalex.org/keywords/adversarial-machine-learning","display_name":"Adversarial machine learning","score":0.40299999713897705}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9422000050544739},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7592999935150146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7185999751091003},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6410999894142151},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5299999713897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5260000228881836},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.459199994802475},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.4120999872684479},{"id":"https://openalex.org/C2778403875","wikidata":"https://www.wikidata.org/wiki/Q20312394","display_name":"Adversarial machine learning","level":3,"score":0.40299999713897705},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37040001153945923},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C122507166","wikidata":"https://www.wikidata.org/wiki/Q628906","display_name":"Crossover","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.3109000027179718},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.29019999504089355},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2854999899864197},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3658373","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3658373","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0466e0bbde3348c49512fa043e7531b7","is_oa":true,"landing_page_url":"https://doaj.org/article/0466e0bbde3348c49512fa043e7531b7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 15928-15944 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3658373","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3658373","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7442058324813843,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2411577903","https://openalex.org/W2773691349","https://openalex.org/W2783963507","https://openalex.org/W2921646645","https://openalex.org/W2962894046","https://openalex.org/W2963898834","https://openalex.org/W2969076652","https://openalex.org/W2981207549","https://openalex.org/W3023238316","https://openalex.org/W3042297159","https://openalex.org/W3089365105","https://openalex.org/W4211006639","https://openalex.org/W4285228542","https://openalex.org/W4285606945","https://openalex.org/W4365796094","https://openalex.org/W4382317710","https://openalex.org/W4393148276","https://openalex.org/W4404420827","https://openalex.org/W4407264220","https://openalex.org/W4409262201","https://openalex.org/W4409262394","https://openalex.org/W4410641171","https://openalex.org/W4411021254","https://openalex.org/W4412164646","https://openalex.org/W4412623774","https://openalex.org/W4415540597","https://openalex.org/W4415797597","https://openalex.org/W4416035410","https://openalex.org/W4416922526","https://openalex.org/W7123356239"],"related_works":[],"abstract_inverted_index":{"In":[0],"complex":[1],"driving":[2],"environments,":[3],"autonomous":[4,95],"agents":[5],"must":[6],"interact":[7],"with":[8,54,167],"diverse":[9],"road":[10],"users":[11],"who":[12],"exhibit":[13],"heterogeneous":[14],"and":[15,112,130,136,165],"often":[16],"unpredictable":[17],"behaviors.":[18],"Traditional":[19],"reinforcement":[20],"learning":[21],"(RL)":[22],"methods":[23],"struggle":[24],"to":[25,57,84,109],"maintain":[26],"robust":[27,154],"performance":[28,138],"in":[29,88,93,139,152],"the":[30,145],"presence":[31],"of":[32,41,148],"adversarial":[33,55,63,140,149],"or":[34,68],"deceptive":[35,86,128],"intent.":[36],"We":[37],"propose":[38],"Adversarial":[39,101],"Theory":[40],"Mind":[42],"Reinforcement":[43],"Learning":[44],"(Adversarial":[45],"ToM-RL),":[46],"a":[47,77],"novel":[48],"framework":[49,161],"that":[50,65,100],"integrates":[51],"cognitive":[52,150],"modeling":[53,151],"training":[56],"improve":[58],"agent":[59],"resilience.":[60],"Unlike":[61],"prior":[62],"RL":[64],"perturbs":[66],"observations":[67],"dynamics,":[69],"our":[70],"method":[71,119],"operates":[72],"on":[73],"belief-level":[74],"perturbations":[75],"within":[76],"partially":[78],"observable":[79],"Markov":[80],"decision":[81],"process":[82],"(POMDP)":[83],"simulate":[85],"intent":[87],"Theory-of-Mind":[89],"reasoning.":[90],"Empirical":[91],"results":[92],"hybrid":[94],"vehicle":[96],"crossover":[97],"scenarios":[98],"demonstrate":[99],"ToM-RL":[102,111,169],"reduces":[103],"collision":[104,134],"rates":[105,115,135],"by":[106,116],"38%":[107],"compared":[108],"standard":[110],"improves":[113],"success":[114],"8.3%.":[117],"Our":[118],"shows":[120],"strong":[121],"robustness":[122],"against":[123],"malicious":[124],"behaviors":[125],"such":[126],"as":[127],"yielding":[129],"late-blocking,":[131],"maintaining":[132],"low":[133],"stable":[137],"traffic.":[141],"These":[142],"findings":[143],"highlight":[144],"critical":[146],"role":[147],"ensuring":[153],"decision-making":[155],"for":[156],"security-sensitive":[157],"multi-agent":[158],"systems.":[159],"The":[160],"is":[162],"general,":[163],"model-agnostic,":[164],"compatible":[166],"existing":[168],"pipelines.":[170]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-29T00:00:00"}