{"id":"https://openalex.org/W7164904359","doi":"https://doi.org/10.48550/arxiv.2606.15165","title":"VLALeaks: Membership Inference Attacks against Vision-Language-Action Models","display_name":"VLALeaks: Membership Inference Attacks against Vision-Language-Action Models","publication_year":2026,"publication_date":"2026-06-13","ids":{"openalex":"https://openalex.org/W7164904359","doi":"https://doi.org/10.48550/arxiv.2606.15165"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.15165","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15165","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.15165","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133601187","display_name":"Xukun Luan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luan, Xukun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138727203","display_name":"Jinyan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jinyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138726710","display_name":"Xuesong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xuesong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085493660","display_name":"Yuanguo Bi","orcid":"https://orcid.org/0000-0002-8424-8542"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bi, Yuanguo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129657014","display_name":"Renjun Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Renjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024426789","display_name":"Z. H. Lei","orcid":"https://orcid.org/0009-0003-5094-0957"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei, Zhongxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138744139","display_name":"Di Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Di","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":0.9570000171661377,"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":0.9570000171661377,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.007600000128149986,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.006599999964237213,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/context","display_name":"Context (archaeology)","score":0.5735999941825867},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5401999950408936},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.4165000021457672},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.4124999940395355},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.40450000762939453},{"id":"https://openalex.org/keywords/randomized-response","display_name":"Randomized response","score":0.3330000042915344},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.3319000005722046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6931999921798706},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5735999941825867},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.557699978351593},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5401999950408936},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.4165000021457672},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33660000562667847},{"id":"https://openalex.org/C2776441110","wikidata":"https://www.wikidata.org/wiki/Q1436628","display_name":"Randomized response","level":3,"score":0.3330000042915344},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3327000141143799},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.28679999709129333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.15165","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15165","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.15165","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15165","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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","score":0.7491022944450378,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language-Action":[0],"(VLA)":[1],"models":[2],"enable":[3],"end-to-end":[4],"robot":[5],"control":[6],"and":[7,37,111,129,134,163],"have":[8],"garnered":[9],"widespread":[10],"attention.":[11],"However,":[12],"the":[13,23,54,68,92,95,137,148],"memorization":[14],"of":[15,26,70,98,152],"training":[16,55],"data":[17,28,34],"inherent":[18],"to":[19,46,53,158],"VLA,":[20],"coupled":[21],"with":[22],"high":[24],"cost":[25],"robotic":[27],"acquisition,":[29],"raises":[30],"serious":[31],"concerns":[32],"regarding":[33],"privacy":[35,61,96,138],"leakage":[36],"intellectual":[38],"property":[39],"infringement.":[40],"Membership":[41],"inference":[42],"attacks":[43],"(MIAs)":[44],"aim":[45],"determine":[47],"whether":[48],"a":[49,59,104],"given":[50],"sample":[51],"belongs":[52],"set.":[56],"While":[57],"representing":[58],"significant":[60],"threat,":[62],"this":[63,75],"attack":[64,113,132],"remains":[65],"underexplored":[66],"in":[67,86,140],"context":[69],"VLA":[71,87,99,120,142,155,165],"models.":[72,88,100,166],"To":[73],"bridge":[74],"gap,":[76],"we":[77],"propose":[78],"VLALeaks,":[79],"which":[80],"is":[81,147],"based":[82],"on":[83,154],"attention":[84],"discrepancies":[85],"We":[89],"reveal,":[90],"for":[91,161],"first":[93,149],"time,":[94],"vulnerabilities":[97,139],"Specifically,":[101],"it":[102],"comprises":[103],"two-stage":[105],"process:":[106],"(1)":[107],"membership":[108,127],"feature":[109],"extraction,":[110],"(2)":[112],"model":[114,143],"construction.":[115],"Experimental":[116],"results":[117],"across":[118],"multiple":[119],"benchmarks":[121],"demonstrate":[122],"that":[123],"VLALeaks":[124],"readily":[125],"reveals":[126],"information":[128],"achieves":[130],"optimal":[131],"AUC":[133],"TPR@1\\%FPR,":[135],"highlighting":[136],"current":[141],"deployments.":[144],"Our":[145],"work":[146],"systematic":[150],"study":[151],"MIAs":[153],"models,":[156],"aiming":[157],"provide":[159],"insights":[160],"secure":[162],"trustworthy":[164]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-17T00:00:00"}