{"id":"https://openalex.org/W7164812927","doi":"https://doi.org/10.48550/arxiv.2606.14032","title":"From Attacks to Curricula: Learnability-Guided Adversarial Training for Safe Autonomous Driving","display_name":"From Attacks to Curricula: Learnability-Guided Adversarial Training for Safe Autonomous Driving","publication_year":2026,"publication_date":"2026-06-12","ids":{"openalex":"https://openalex.org/W7164812927","doi":"https://doi.org/10.48550/arxiv.2606.14032"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.14032","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.14032","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.2606.14032","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138687455","display_name":"Yuewen Mei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mei, Yuewen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138633850","display_name":"Tong Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nie, Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138641094","display_name":"Jie Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138668809","display_name":"Haotian Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Haotian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138672718","display_name":"Wei Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138636758","display_name":"Jian Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Jian","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9763000011444092,"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":0.9763000011444092,"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":0.012900000438094139,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.00139999995008111,"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":0.8385000228881836},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.5490999817848206},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5324000120162964},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5091999769210815},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4867999851703644},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.4661000072956085},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4560999870300293},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.44339999556541443},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.435699999332428}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8385000228881836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6284999847412109},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.5490999817848206},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5324000120162964},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5091999769210815},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.4661000072956085},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4560999870300293},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.44339999556541443},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.435699999332428},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.42649999260902405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4198000133037567},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.37540000677108765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3675999939441681},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.3025999963283539},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.27720001339912415},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2653999924659729},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.14032","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.14032","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.2606.14032","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.14032","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":[{"display_name":"Quality Education","score":0.4696732759475708,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Closed-loop":[0],"adversarial":[1,18,67,72,82,195],"training":[2,68,172],"improves":[3,165],"autonomous":[4,220],"driving":[5,53,221],"safety":[6],"by":[7,174],"exposing":[8],"policies":[9],"to":[10,95,109,176,207],"rare":[11],"safety-critical":[12],"scenarios.":[13,103],"Standard":[14],"pipelines":[15],"first":[16],"generate":[17],"scenarios":[19,73,136,149],"and":[20,58,76,90,118,168,187,194,217],"then":[21],"sample":[22,56],"them":[23],"for":[24,215],"policy":[25,117,127,209],"optimization.":[26],"However,":[27],"most":[28],"existing":[29],"frameworks":[30],"remain":[31],"attack-oriented:":[32],"collision-driven":[33],"generators":[34],"often":[35],"synthesize":[36],"unsolvable":[37],"extreme":[38],"situations,":[39],"which":[40],"can":[41],"degrade":[42],"learning,":[43],"while":[44,183],"heuristic":[45],"samplers":[46],"ignore":[47],"the":[48,52,97,111,115,151,157],"evolving":[49,116],"capability":[50,122,138],"of":[51,114],"policy,":[54],"causing":[55],"inefficiency":[57],"delayed":[59],"convergence.":[60],"We":[61],"propose":[62],"AlignADV,":[63],"a":[64,86,120,142,201,212],"learnability-guided":[65,208],"closed-loop":[66,131],"framework":[69],"that":[70,125,147,163],"converts":[71],"into":[74],"resolvable":[75,102],"capability-aligned":[77],"curricula.":[78],"First,":[79],"we":[80,105],"reformulate":[81],"scenario":[83,205],"generation":[84,206],"as":[85],"preference":[87,93],"alignment":[88],"problem":[89],"employ":[91],"direct":[92],"optimization":[94],"guide":[96],"generator":[98],"toward":[99],"critical":[100],"yet":[101],"Second,":[104],"introduce":[106],"behavioral":[107],"fingerprints":[108],"capture":[110],"intrinsic":[112],"characteristics":[113],"construct":[119],"multi-modal":[121],"prediction":[123],"model":[124],"estimates":[126],"performance":[128],"without":[129],"expensive":[130],"simulations.":[132],"By":[133],"combining":[134],"resolvability-aligned":[135],"with":[137,180],"predictions,":[139],"AlignADV":[140,164],"develops":[141],"dynamic":[143],"curriculum":[144],"sampling":[145],"mechanism":[146],"prioritizes":[148],"targeting":[150],"current":[152],"policy's":[153],"vulnerabilities.":[154],"Experiments":[155],"on":[156],"Waymo":[158],"Open":[159],"Motion":[160],"Dataset":[161],"demonstrate":[162],"convergence":[166],"efficiency":[167],"final":[169],"performance,":[170],"reducing":[171],"steps":[173],"up":[175],"40.6":[177],"percent":[178],"compared":[179],"baseline":[181],"methods":[182],"lowering":[184],"collision":[185],"rate":[186],"improving":[188],"route":[189],"completion":[190],"under":[191],"both":[192],"normal":[193],"traffic":[196],"conditions.":[197],"These":[198],"results":[199],"highlight":[200],"shift":[202],"from":[203],"attack-oriented":[204],"improvement,":[210],"offering":[211],"principled":[213],"direction":[214],"safer":[216],"more":[218],"efficient":[219],"training.":[222],"Project":[223],"page:":[224],"https://meiyuewen.github.io/AlignADV/.":[225]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-16T00:00:00"}