{"id":"https://openalex.org/W4412445643","doi":"https://doi.org/10.1109/noms57970.2025.11073724","title":"Adversarial Autoencoder based Model Extraction Attacks for Collaborative DNN Inference at Edge","display_name":"Adversarial Autoencoder based Model Extraction Attacks for Collaborative DNN Inference at Edge","publication_year":2025,"publication_date":"2025-05-12","ids":{"openalex":"https://openalex.org/W4412445643","doi":"https://doi.org/10.1109/noms57970.2025.11073724"},"language":"en","primary_location":{"id":"doi:10.1109/noms57970.2025.11073724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/noms57970.2025.11073724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"NOMS 2025-2025 IEEE Network Operations and Management Symposium","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118995386","display_name":"Manal Zneit","orcid":null},"institutions":[{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Manal Zneit","raw_affiliation_strings":["City University of New York"],"affiliations":[{"raw_affiliation_string":"City University of New York","institution_ids":["https://openalex.org/I174216632"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100718556","display_name":"Xiaojie Zhang","orcid":"https://orcid.org/0009-0005-6576-1876"},"institutions":[{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaojie Zhang","raw_affiliation_strings":["City University of New York"],"affiliations":[{"raw_affiliation_string":"City University of New York","institution_ids":["https://openalex.org/I174216632"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074308655","display_name":"Motahare Mounesan","orcid":null},"institutions":[{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Motahare Mounesan","raw_affiliation_strings":["City University of New York"],"affiliations":[{"raw_affiliation_string":"City University of New York","institution_ids":["https://openalex.org/I174216632"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015917097","display_name":"Saptarshi Debroy","orcid":"https://orcid.org/0000-0002-4783-119X"},"institutions":[{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saptarshi Debroy","raw_affiliation_strings":["City University of New York"],"affiliations":[{"raw_affiliation_string":"City University of New York","institution_ids":["https://openalex.org/I174216632"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5118995386"],"corresponding_institution_ids":["https://openalex.org/I174216632"],"apc_list":null,"apc_paid":null,"fwci":5.7199,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9582543,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"09"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9973999857902527,"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":0.9973999857902527,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9948999881744385,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9696999788284302,"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/autoencoder","display_name":"Autoencoder","score":0.9071375727653503},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7470894455909729},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6793027520179749},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6266566514968872},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5963011384010315},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5762972235679626},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5180785655975342},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44702059030532837},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38698697090148926},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3619576692581177},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.30412524938583374}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9071375727653503},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7470894455909729},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6793027520179749},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6266566514968872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5963011384010315},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5762972235679626},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5180785655975342},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44702059030532837},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38698697090148926},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3619576692581177},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30412524938583374},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/noms57970.2025.11073724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/noms57970.2025.11073724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"NOMS 2025-2025 IEEE Network Operations and Management Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G351994607","display_name":null,"funder_award_id":"CNS-1943338,CNS-2401928","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2147768505","https://openalex.org/W2293078015","https://openalex.org/W2591882872","https://openalex.org/W2605258629","https://openalex.org/W2789304371","https://openalex.org/W2963327228","https://openalex.org/W2963456518","https://openalex.org/W2969695741","https://openalex.org/W2980856918","https://openalex.org/W2989885118","https://openalex.org/W3014022300","https://openalex.org/W3014879164","https://openalex.org/W3044591330","https://openalex.org/W3045917937","https://openalex.org/W3118608800","https://openalex.org/W3119841746","https://openalex.org/W3163488673","https://openalex.org/W3182125009","https://openalex.org/W3188107178","https://openalex.org/W3199355384","https://openalex.org/W3204676010","https://openalex.org/W4246001895","https://openalex.org/W4289146347","https://openalex.org/W4297846303","https://openalex.org/W4306920798","https://openalex.org/W4385489040","https://openalex.org/W4400234282","https://openalex.org/W4405935501","https://openalex.org/W6754619707","https://openalex.org/W6780010867"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2159052453","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W2502115930","https://openalex.org/W2803255133","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"are":[4],"influencing":[5],"a":[6,39,87,127],"wide":[7],"range":[8],"of":[9,135,176,189],"applications":[10],"from":[11],"safety-critical":[12],"to":[13,63,78,96,123,151],"security-sensitive":[14],"use":[15,20],"cases.":[16],"In":[17,82],"many":[18,192],"such":[19,56,94],"cases,":[21],"the":[22,49,67,100,107,113,133,136,149,157,174,177,183],"DNN":[23,41,60,88,110,170],"inference":[24],"process":[25],"relies":[26],"on":[27],"distributed":[28],"systems":[29],"involving":[30],"IoT":[31],"devices":[32],"and":[33,48,120,125,145,160],"edge/cloud":[34],"severs":[35],"as":[36],"participants":[37,50,68],"where":[38],"pre-trained":[40],"model":[42,89,116,129,159,180,185],"is":[43,143],"partitioned/split":[44],"onto":[45],"multiple":[46],"parts":[47],"collaboratively":[51],"execute":[52],"them.":[53],"However,":[54],"often":[55],"collaboration":[57],"requires":[58],"dynamic":[59],"partitioning":[61],"information":[62,155],"be":[64],"exchanged":[65],"among":[66],"over":[69],"unsecured":[70],"network":[71],"or":[72],"via":[73],"relays/hops":[74],"which":[75],"can":[76],"lead":[77],"novel":[79],"privacy":[80],"vulnerabilities.":[81],"this":[83],"paper,":[84],"we":[85,172],"propose":[86],"extraction":[90],"attack":[91,115,142,179],"that":[92,130],"exploits":[93],"vulnerabilities":[95],"not":[97,147],"only":[98],"extract":[99],"original":[101,137],"input":[102,161],"data,":[103],"but":[104],"also":[105],"reconstruct":[106],"entire":[108],"victim":[109,138,158,184],"model.":[111,139],"Specifically,":[112],"proposed":[114,141,178],"utilizes":[117],"extracted/leaked":[118],"data":[119],"adversarial":[121],"autoencoders":[122],"generate":[124],"train":[126],"shadow":[128],"closely":[131],"mimics":[132],"behavior":[134],"The":[140],"query-free":[144],"does":[146],"require":[148],"attacker":[150],"have":[152],"any":[153],"prior":[154],"about":[156],"data.":[162],"Using":[163],"an":[164],"IoT-edge":[165],"hardware":[166],"testbed":[167],"running":[168],"collaborative":[169],"inference,":[171],"demonstrate":[173],"effectiveness":[175],"in":[181],"extracting":[182],"with":[186],"high":[187],"levels":[188],"certainty":[190],"across":[191],"realistic":[193],"scenarios.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}