{"id":"https://openalex.org/W4401943774","doi":"https://doi.org/10.1109/cloud62652.2024.00028","title":"Securing AI Inference in the Cloud: Is CPU-GPU Confidential Computing Ready?","display_name":"Securing AI Inference in the Cloud: Is CPU-GPU Confidential Computing Ready?","publication_year":2024,"publication_date":"2024-07-07","ids":{"openalex":"https://openalex.org/W4401943774","doi":"https://doi.org/10.1109/cloud62652.2024.00028"},"language":"en","primary_location":{"id":"doi:10.1109/cloud62652.2024.00028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cloud62652.2024.00028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 17th International Conference on Cloud Computing (CLOUD)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5080887047","display_name":"Apoorve Mohan","orcid":"https://orcid.org/0000-0003-3789-5453"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Apoorve Mohan","raw_affiliation_strings":["IBM T.J. Watson Research Center,Yorktown Heights,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center,Yorktown Heights,New York,USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065008304","display_name":"Mengmei Ye","orcid":"https://orcid.org/0000-0002-3434-1968"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengmei Ye","raw_affiliation_strings":["IBM T.J. Watson Research Center,Yorktown Heights,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center,Yorktown Heights,New York,USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038903691","display_name":"Hubertus Franke","orcid":"https://orcid.org/0009-0005-0150-1055"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hubertus Franke","raw_affiliation_strings":["IBM T.J. Watson Research Center,Yorktown Heights,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center,Yorktown Heights,New York,USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072108555","display_name":"Mudhakar Srivatsa","orcid":"https://orcid.org/0000-0002-5874-3750"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mudhakar Srivatsa","raw_affiliation_strings":["IBM T.J. Watson Research Center,Yorktown Heights,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center,Yorktown Heights,New York,USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108929515","display_name":"Zhuoran Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuoran Liu","raw_affiliation_strings":["IBM T.J. Watson Research Center,Yorktown Heights,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center,Yorktown Heights,New York,USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102979275","display_name":"Nelson Mimura Gonzalez","orcid":"https://orcid.org/0000-0002-8313-8114"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nelson Mimura Gonzalez","raw_affiliation_strings":["IBM T.J. Watson Research Center,Yorktown Heights,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center,Yorktown Heights,New York,USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":10.598,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.98695957,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"164","last_page":"175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11614","display_name":"Cloud Data Security Solutions","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11424","display_name":"Security and Verification in Computing","score":0.991599977016449,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9804999828338623,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/cloud-computing","display_name":"Cloud computing","score":0.8383268117904663},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7898939847946167},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6484472155570984},{"id":"https://openalex.org/keywords/confidentiality","display_name":"Confidentiality","score":0.6459556818008423},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3248031735420227},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3232617974281311},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.30819737911224365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16328391432762146}],"concepts":[{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.8383268117904663},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7898939847946167},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6484472155570984},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.6459556818008423},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3248031735420227},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3232617974281311},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.30819737911224365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16328391432762146}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cloud62652.2024.00028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cloud62652.2024.00028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 17th International Conference on Cloud Computing (CLOUD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W107524893","https://openalex.org/W1252105715","https://openalex.org/W1922926746","https://openalex.org/W1973211560","https://openalex.org/W1983157164","https://openalex.org/W2038235314","https://openalex.org/W2483945477","https://openalex.org/W2559755452","https://openalex.org/W2734941459","https://openalex.org/W2896457183","https://openalex.org/W2913096406","https://openalex.org/W2932835273","https://openalex.org/W3081879387","https://openalex.org/W3098304703","https://openalex.org/W3125079283","https://openalex.org/W3141199462","https://openalex.org/W3159718887","https://openalex.org/W3174854792","https://openalex.org/W3213416239","https://openalex.org/W4280633999","https://openalex.org/W4293024088","https://openalex.org/W4322718191","https://openalex.org/W4385245566","https://openalex.org/W4386502612","https://openalex.org/W4386764604","https://openalex.org/W4389279126","https://openalex.org/W4392806465","https://openalex.org/W4396814788","https://openalex.org/W6739901393","https://openalex.org/W6743073161","https://openalex.org/W6748463777","https://openalex.org/W6755958147","https://openalex.org/W6765586001","https://openalex.org/W6780010867"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2091483479"],"abstract_inverted_index":{"Many":[0],"applications":[1,117],"have":[2,71],"been":[3],"offloaded":[4,118],"onto":[5],"cloud":[6,24,68],"environments":[7,25,85],"to":[8,13,56,61,73,76,93,110,119,204,230],"achieve":[9],"higher":[10],"agility,":[11],"access":[12],"more":[14],"powerful":[15],"computational":[16],"resources,":[17],"and":[18,45,48,80,113,164,172,178,183,208],"obtain":[19],"better":[20],"infrastructure":[21],"management.":[22],"Although":[23],"provide":[26,184],"solid":[27],"security":[28],"solutions,":[29],"users":[30],"with":[31,214,232],"highly":[32],"sensitive":[33,203],"data":[34,78],"or":[35],"regulatory":[36],"compliance":[37],"requirements,":[38],"such":[39,58,121],"as":[40,122],"HIPAA":[41],"(Health":[42],"Insurance":[43],"Portability":[44],"Accountability":[46],"Act)":[47],"GDPR":[49],"(General":[50],"Data":[51],"Protection":[52],"Regulation),":[53],"still":[54],"hesitate":[55],"move":[57],"application":[59],"domains":[60],"the":[62,102,187,205,219],"cloud.":[63],"To":[64],"address":[65],"these":[66,90],"concerns,":[67],"service":[69],"providers":[70],"started":[72],"offer":[74],"solutions":[75],"protect":[77],"confidentiality":[79,112],"integrity":[81,114],"through":[82,168],"trusted":[83],"execution":[84],"(TEEs).":[86],"While":[87],"so":[88],"far":[89],"were":[91],"limited":[92],"CPU":[94],"TEEs":[95,226],"only,":[96],"NVIDIA's":[97],"Hopper":[98],"architecture":[99],"has":[100],"shifted":[101],"landscape":[103],"by":[104,190],"enabling":[105],"confidential":[106,138,155,191],"computing":[107,139,156,192],"features":[108],"essential":[109],"protecting":[111],"for":[115],"real-world":[116],"GPUs,":[120],"large":[123,180],"language":[124,181],"models":[125,182,213],"(LLMs).":[126],"However,":[127],"there":[128],"lacks":[129],"a":[130,142,146,154],"sufficient":[131],"study":[132],"on":[133,186],"how":[134],"much":[135],"performance":[136,220],"overhead":[137,188],"introduces":[140],"in":[141,224],"TEE":[143],"comprised":[144,158],"of":[145,159,221],"CPU-GPU":[147,225],"configuration.":[148],"In":[149],"this":[150],"paper":[151],"we":[152],"evaluate":[153],"environment":[157],"an":[160],"Intel":[161],"TDX":[162],"system":[163],"NVIDIA":[165],"H100":[166],"GPUs":[167,194],"various":[169],"micro":[170],"benchmarks":[171],"real":[173],"workloads":[174],"including":[175],"BERT,":[176],"LLaMA,":[177],"Granite":[179],"discussions":[185],"incurred":[189],"when":[193,211],"are":[195,202,217],"utilized.":[196],"We":[197],"show":[198],"that":[199],"while":[200],"LLMs":[201],"model":[206],"types":[207],"batch":[209],"sizes,":[210],"larger":[212],"pipelined":[215],"processing":[216],"deployed,":[218],"LLM":[222],"inference":[223],"can":[227],"be":[228],"close":[229],"par":[231],"their":[233],"non-confidential":[234],"setups.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}