{"id":"https://openalex.org/W7124854699","doi":"https://doi.org/10.1109/cloudcom67567.2025.11331361","title":"Between Generation and Judgment: A Cloud-Native Framework for Adversarial Evaluation of LLM Alignment","display_name":"Between Generation and Judgment: A Cloud-Native Framework for Adversarial Evaluation of LLM Alignment","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W7124854699","doi":"https://doi.org/10.1109/cloudcom67567.2025.11331361"},"language":null,"primary_location":{"id":"doi:10.1109/cloudcom67567.2025.11331361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cloudcom67567.2025.11331361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 lEEE International Conference on Cloud Computing Technology and Science (CloudCom)","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/A5123450062","display_name":"Diego E. G. Caetano De Oliveira","orcid":null},"institutions":[{"id":"https://openalex.org/I164790352","display_name":"Universidade do Estado de Santa Catarina","ror":"https://ror.org/03ztsbk67","country_code":"BR","type":"education","lineage":["https://openalex.org/I164790352"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Diego E. G. Caetano De Oliveira","raw_affiliation_strings":["Universidade do Estado de Santa Catarina (UDESC),Department of Computer Science,Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade do Estado de Santa Catarina (UDESC),Department of Computer Science,Brazil","institution_ids":["https://openalex.org/I164790352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077382160","display_name":"Charles C. Miers","orcid":"https://orcid.org/0000-0002-1976-0478"},"institutions":[{"id":"https://openalex.org/I164790352","display_name":"Universidade do Estado de Santa Catarina","ror":"https://ror.org/03ztsbk67","country_code":"BR","type":"education","lineage":["https://openalex.org/I164790352"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Charles C. Miers","raw_affiliation_strings":["Universidade do Estado de Santa Catarina (UDESC),Department of Computer Science,Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade do Estado de Santa Catarina (UDESC),Department of Computer Science,Brazil","institution_ids":["https://openalex.org/I164790352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107470447","display_name":"Marcos A. Simplicio","orcid":null},"institutions":[{"id":"https://openalex.org/I3019322962","display_name":"Universidade Brasil","ror":"https://ror.org/04031z735","country_code":"BR","type":"education","lineage":["https://openalex.org/I3019322962"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcos A. Simplicio","raw_affiliation_strings":["Universidade de S&#x00E3;o Paulo (USP),Department of Computer Engineering (PCS),Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade de S&#x00E3;o Paulo (USP),Department of Computer Engineering (PCS),Brazil","institution_ids":["https://openalex.org/I3019322962"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058562603","display_name":"Victor Takashi Hayashi","orcid":"https://orcid.org/0000-0001-6672-4296"},"institutions":[{"id":"https://openalex.org/I3019322962","display_name":"Universidade Brasil","ror":"https://ror.org/04031z735","country_code":"BR","type":"education","lineage":["https://openalex.org/I3019322962"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Victor Takashi Hayashi","raw_affiliation_strings":["Universidade de S&#x00E3;o Paulo (USP),Department of Computer Engineering (PCS),Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade de S&#x00E3;o Paulo (USP),Department of Computer Engineering (PCS),Brazil","institution_ids":["https://openalex.org/I3019322962"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5123450062"],"corresponding_institution_ids":["https://openalex.org/I164790352"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.82638673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.2809000015258789,"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":0.2809000015258789,"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/T11424","display_name":"Security and Verification in Computing","score":0.12080000340938568,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.11400000005960464,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8151999711990356},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5934000015258789},{"id":"https://openalex.org/keywords/adjudication","display_name":"Adjudication","score":0.564300000667572},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5322999954223633},{"id":"https://openalex.org/keywords/blueprint","display_name":"Blueprint","score":0.4844000041484833},{"id":"https://openalex.org/keywords/triage","display_name":"Triage","score":0.3804999887943268},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.3416000008583069}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8151999711990356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.670799970626831},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5934000015258789},{"id":"https://openalex.org/C204434341","wikidata":"https://www.wikidata.org/wiki/Q357789","display_name":"Adjudication","level":2,"score":0.564300000667572},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5322999954223633},{"id":"https://openalex.org/C155911762","wikidata":"https://www.wikidata.org/wiki/Q422321","display_name":"Blueprint","level":2,"score":0.4844000041484833},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.38510000705718994},{"id":"https://openalex.org/C2777120189","wikidata":"https://www.wikidata.org/wiki/Q780067","display_name":"Triage","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35499998927116394},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C125209513","wikidata":"https://www.wikidata.org/wiki/Q4037520","display_name":"Doors","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27630001306533813},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2700999975204468}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cloudcom67567.2025.11331361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cloudcom67567.2025.11331361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 lEEE International Conference on Cloud Computing Technology and Science (CloudCom)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.45835670828819275,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1892344100","display_name":null,"funder_award_id":"2020/09850\u20130","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"}],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"},{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320323349","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa e Inova\u00e7\u00e3o do Estado de Santa Catarina","ror":"https://ror.org/0503xdx77"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4401042259"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,12,112,126],"cloud-native,":[3],"end-to-end":[4],"pipeline":[5],"that":[6],"unifies":[7],"automated":[8],"attack":[9],"generation":[10],"with":[11],"modular":[13],"LLM-as-a-Judge,":[14],"supports":[15],"static/adaptive":[16],"corpora":[17],"across":[18],"open":[19],"and":[20,27,38,65,95,120],"proprietary":[21],"models,":[22],"enables":[23],"calibrated":[24],"multi-judge":[25],"consensus,":[26],"emits":[28],"audit-ready":[29],"cost/latency":[30],"telemetry-addressing":[31],"gaps":[32],"from":[33,71],"non-cloud-native":[34],"scripts,":[35],"decoupled":[36],"attack/judgment,":[37],"single-judge":[39],"bias.":[40],"Evaluated":[41],"under":[42],"two":[43],"budgets":[44],"(MAX_PROMPTS":[45],"<tex":[46,56,88,103],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[47,57,89,104],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$=10,32)$</tex>":[48],"on":[49],"three":[50],"targets-Llama":[51],"3.3":[52,75],"70B":[53,76],"Instruct,":[54,60],"Mix-tral":[55],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$8\\times":[58],"7\\mathrm{B}$</tex>":[59],"DeepSeek-V3-ASR":[61],"spans":[62],"0-37.5%":[63],"(10)":[64],"0-26.6%":[66],"(32);":[67],"judge":[68],"accuracy":[69],"ranges":[70],"92.93%":[72],"(open":[73],"Llama":[74],"Instruct)":[77],"to":[78],"98.94%":[79],"(proprietary":[80],"GPT-4o);":[81],"mean":[82],"judgment":[83],"latency":[84],"is":[85,98],"1.2-5.6":[86],"s":[87],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\text":[90],"{":[91],"(GPT-4o":[92],"DeepSeek-V3)":[93],"}$</tex>;":[94],"unit":[96],"cost":[97],"$0.10-$2.18":[99],"per":[100],"lk":[101],"adjudications":[102],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$(\\text{Mixtral}8\\times":[105],"7\\mathrm{B}":[106],"\\rightarrow":[107],"\\text{GPT}-40)$</tex>.":[108],"These":[109],"results":[110],"motivate":[111],"tiered":[113],"policy-lightweight":[114],"open-family":[115],"judges":[116,122],"for":[117,123,129],"high-throughput":[118],"triage":[119],"cross-family/ensemble":[121],"low-confidence":[124],"cases-offering":[125],"practical":[127],"blueprint":[128],"continuous,":[130],"auditable":[131],"adversarial":[132],"eval-uation":[133],"of":[134],"LLM":[135],"alignment":[136],"at":[137],"cloud":[138],"scale.":[139]},"counts_by_year":[],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2026-01-21T00:00:00"}
