{"id":"https://openalex.org/W7225610586","doi":"https://doi.org/10.3390/jcp6060196","title":"Preserving Malicious Client Detectability Under Differential Privacy Through Temporal Multi-Relation Graph Learning","display_name":"Preserving Malicious Client Detectability Under Differential Privacy Through Temporal Multi-Relation Graph Learning","publication_year":2026,"publication_date":"2026-11-08","ids":{"openalex":"https://openalex.org/W7225610586","doi":"https://doi.org/10.3390/jcp6060196"},"language":"en","primary_location":{"id":"doi:10.3390/jcp6060196","doi":"https://doi.org/10.3390/jcp6060196","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jcp6060196","pdf_url":null,"source":{"id":"https://openalex.org/S4210232532","display_name":"Journal of Cybersecurity and Privacy","issn_l":"2624-800X","issn":["2624-800X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cybersecurity and Privacy","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/jcp6060196","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120627798","display_name":"Anuja Kunjumon","orcid":"https://orcid.org/0009-0009-7700-6762","observed_orcids":["https://orcid.org/0009-0009-7700-6762"]},"institutions":[{"id":"https://openalex.org/I81556334","display_name":"Amrita Vishwa Vidyapeetham","ror":"https://ror.org/03am10p12","country_code":"IN","type":"education","lineage":["https://openalex.org/I81556334"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anuja Kunjumon","raw_affiliation_strings":["Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri, Kollam 690525, Kerala, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri, Kollam 690525, Kerala, India","institution_ids":["https://openalex.org/I81556334"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035990258","display_name":"Sunitha Edacheril Viswanathan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I81556334","display_name":"Amrita Vishwa Vidyapeetham","ror":"https://ror.org/03am10p12","country_code":"IN","type":"education","lineage":["https://openalex.org/I81556334"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sunitha E. Viswanathan","raw_affiliation_strings":["Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri, Kollam 690525, Kerala, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri, Kollam 690525, Kerala, India","institution_ids":["https://openalex.org/I81556334"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041549614","display_name":"Jyothisha J. Nair","orcid":"https://orcid.org/0000-0002-8050-8896","observed_orcids":["https://orcid.org/0000-0002-8050-8896"]},"institutions":[{"id":"https://openalex.org/I177436651","display_name":"Mahatma Gandhi University","ror":"https://ror.org/00h4spn88","country_code":"IN","type":"education","lineage":["https://openalex.org/I177436651"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jyothisha J. Nair","raw_affiliation_strings":["School of Computer Sciences, Mahatma Gandhi University, Kottayam 686560, Kerala, India"],"raw_orcid":"https://orcid.org/0000-0002-8050-8896","affiliations":[{"raw_affiliation_string":"School of Computer Sciences, Mahatma Gandhi University, Kottayam 686560, Kerala, India","institution_ids":["https://openalex.org/I177436651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035990258"],"corresponding_institution_ids":["https://openalex.org/I81556334"],"apc_list":{"value":1000,"currency":"CHF","value_usd":1207},"apc_paid":{"value":1000,"currency":"CHF","value_usd":1207},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":"6","first_page":"196","last_page":"196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":1.0,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":1.0,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":9.999999747378752e-05,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.0,"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/malicious-client-detection","display_name":"malicious client detection","score":0.984000027179718},{"id":"https://openalex.org/keywords/federated-learning","display_name":"federated learning","score":0.8410000205039978},{"id":"https://openalex.org/keywords/differential-privacy","display_name":"differential privacy","score":0.9990000128746033},{"id":"https://openalex.org/keywords/privacy-preserving-detection","display_name":"privacy-preserving detection","score":0.6690000295639038},{"id":"https://openalex.org/keywords/sybil-attack","display_name":"Sybil attack","score":0.902999997138977},{"id":"https://openalex.org/keywords/backdoor-attacks","display_name":"backdoor attacks","score":0.7749999761581421},{"id":"https://openalex.org/keywords/non-iid-data","display_name":"non-IID data","score":0.8920000195503235},{"id":"https://openalex.org/keywords/robust-aggregation","display_name":"robust aggregation","score":0.4790000021457672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8346999883651733},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.8291000127792358},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.48539999127388},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41760000586509705},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39489999413490295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37369999289512634},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3707999885082245},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.35519999265670776},{"id":"https://openalex.org/C133710760","wikidata":"https://www.wikidata.org/wiki/Q775837","display_name":"Exponential smoothing","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C112789634","wikidata":"https://www.wikidata.org/wiki/Q18207010","display_name":"False positives and false negatives","level":3,"score":0.3422999978065491},{"id":"https://openalex.org/C40305131","wikidata":"https://www.wikidata.org/wiki/Q2616305","display_name":"Obfuscation","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C2780909371","wikidata":"https://www.wikidata.org/wiki/Q4801092","display_name":"Artificial noise","level":4,"score":0.33090001344680786},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C2780821482","wikidata":"https://www.wikidata.org/wiki/Q25381721","display_name":"Crowdsensing","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C3017597292","wikidata":"https://www.wikidata.org/wiki/Q25052250","display_name":"Privacy protection","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.27379998564720154},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C148417208","wikidata":"https://www.wikidata.org/wiki/Q4825882","display_name":"Authentication (law)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C2780771206","wikidata":"https://www.wikidata.org/wiki/Q3271761","display_name":"Safeguard","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/jcp6060196","doi":"https://doi.org/10.3390/jcp6060196","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jcp6060196","pdf_url":null,"source":{"id":"https://openalex.org/S4210232532","display_name":"Journal of Cybersecurity and Privacy","issn_l":"2624-800X","issn":["2624-800X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cybersecurity and Privacy","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/jcp6060196","doi":"https://doi.org/10.3390/jcp6060196","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jcp6060196","pdf_url":null,"source":{"id":"https://openalex.org/S4210232532","display_name":"Journal of Cybersecurity and Privacy","issn_l":"2624-800X","issn":["2624-800X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cybersecurity and Privacy","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W3200256144","https://openalex.org/W4322576473","https://openalex.org/W4366815236","https://openalex.org/W4382281941","https://openalex.org/W4384499048","https://openalex.org/W4387449166","https://openalex.org/W4391661565","https://openalex.org/W4392477550","https://openalex.org/W4394699144","https://openalex.org/W4401027226","https://openalex.org/W4404030380","https://openalex.org/W4404739159","https://openalex.org/W4406269727","https://openalex.org/W4406415738","https://openalex.org/W4407317340","https://openalex.org/W4409762138","https://openalex.org/W4409985428","https://openalex.org/W4412811394","https://openalex.org/W4413008556","https://openalex.org/W4413118578","https://openalex.org/W4413176721","https://openalex.org/W4415950832","https://openalex.org/W7115924300","https://openalex.org/W7117482713","https://openalex.org/W7124450903","https://openalex.org/W7131091546","https://openalex.org/W7135226767","https://openalex.org/W7137155252","https://openalex.org/W7160291994","https://openalex.org/W7162449325","https://openalex.org/W7165736448"],"related_works":["https://openalex.org/W4408400210","https://openalex.org/W4407317340","https://openalex.org/W7095001465","https://openalex.org/W7162851765","https://openalex.org/W4384499048","https://openalex.org/W3189326969","https://openalex.org/W4392477550","https://openalex.org/W2777914285","https://openalex.org/W4220764289","https://openalex.org/W4408819655"],"abstract_inverted_index":{"Federated":[0],"learning":[1,19,119],"has":[2],"emerged":[3],"as":[4],"a":[5,11,104,113,254,280,286,291],"privacy-preserving":[6,115],"paradigm":[7],"that":[8,63,80,106,159,248,299,335],"collaboratively":[9],"trains":[10],"model":[12,265],"without":[13],"sharing":[14],"raw":[15],"data.":[16],"However,":[17,69],"federated":[18,39],"remains":[20],"highly":[21],"vulnerable":[22],"to":[23,34,49,87,125,163,178,188,313],"abnormal":[24],"or":[25],"malicious":[26,52,55,92,127,243,258,300,325],"participants.":[27],"Differential":[28],"privacy":[29,44,98,164,268,293,309,332],"techniques":[30,58],"are":[31,66,72,176],"widely":[32],"adopted":[33],"safeguard":[35],"client":[36,56,82,244,259,301,326],"data":[37,211],"during":[38],"optimization,":[40],"but":[41],"the":[42,60,77,123,130,138,147,153,249,273,277,317,322],"added":[43],"noise":[45],"makes":[46],"it":[47,85],"harder":[48,86],"detect":[50,126],"such":[51],"behaviors.":[53],"Existing":[54],"detection":[57,102,245,260,281,302,315],"make":[59],"implicit":[61],"assumption":[62],"behavioral":[64,157],"signals":[65,71],"still":[67,108],"identifiable.":[68],"these":[70],"distorted":[73,161],"by":[74,228,329],"differential":[75,331],"privacy,":[76],"very":[78],"mechanism":[79],"protects":[81],"information,":[83],"making":[84],"identify":[88],"between":[89],"benign":[90],"and":[91,140,172,182,204,209,222,234,241,267,285,333],"clients.":[93],"Because":[94],"of":[95,144,283,288,295,324],"this,":[96],"enhancing":[97],"often":[99],"reduces":[100],"attack":[101,262],"effectiveness,":[103],"problem":[105],"is":[107,160,194],"mostly":[109],"unsolved.":[110],"We":[111],"present":[112],"new":[114],"temporal":[116,139,174,336],"multi-relational":[117],"graph":[118],"framework,":[120],"which":[121],"improves":[122],"ability":[124],"clients":[128,145],"in":[129],"differentially":[131],"private":[132],"setting.":[133],"By":[134],"taking":[135],"into":[136],"account":[137],"relational":[141,337],"dependency":[142],"structures":[143],"through":[146],"communication":[148],"rounds,":[149],"our":[150],"framework":[151,193],"minimizes":[152],"dependence":[154],"on":[155,197],"single":[156],"information":[158],"due":[162,187],"noise.":[165],"In":[166,311],"addition,":[167],"exponential":[168],"moving":[169],"average":[170],"smoothing":[171],"persistence-based":[173],"voting":[175],"introduced":[177],"ensure":[179],"detector":[180,278],"stability":[181],"minimize":[183],"potential":[184],"false":[185],"positives":[186],"privacy-induced":[189],"perturbations.":[190],"The":[191],"proposed":[192,250,318],"comprehensively":[195],"evaluated":[196],"three":[198],"benchmark":[199],"datasets,":[200],"namely,":[201],"FashionMNIST,":[202],"CSE-CIC-IDS2018,":[203],"CIC-IoT2023,":[205,271],"under":[206,272],"both":[207],"IID":[208],"non-IID":[210,274],"distributions":[212],"across":[213],"diverse":[214],"adversarial":[215],"scenarios,":[216],"including":[217],"label-flip,":[218],"backdoor,":[219],"gradient-lie,":[220],"free-rider,":[221],"Sybil":[223],"attacks.":[224],"Experimental":[225],"evaluation,":[226],"supported":[227],"privacy-budget":[229],"analysis,":[230],"component-wise":[231],"ablation":[232],"studies,":[233],"comparisons":[235],"with":[236],"representative":[237],"robust":[238],"aggregation":[239],"methods":[240],"recent":[242],"baselines,":[246],"demonstrates":[247],"approach":[251],"consistently":[252],"achieves":[253],"better":[255],"balance":[256],"among":[257],"accuracy,":[261],"mitigation,":[263],"global":[264],"utility,":[266],"preservation.":[269],"On":[270],"gradient-lie":[275],"attack,":[276],"achieved":[279],"accuracy":[282],"0.8467\u00b10.0231":[284],"recall":[287],"1.0000\u00b10.0000":[289],"at":[290],"composed":[292],"budget":[294],"approximately":[296],"\u03f5total=7.05,":[297],"demonstrating":[298],"can":[303],"be":[304],"retained":[305],"while":[306],"providing":[307],"stronger":[308],"protection.":[310],"addition":[312],"improving":[314],"performance,":[316],"work":[319],"quantitatively":[320],"assesses":[321],"degradation":[323],"separability":[327],"caused":[328],"increased":[330],"shows":[334],"modeling":[338],"significantly":[339],"mitigates":[340],"this":[341],"effect.":[342]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}