LEADER 04992nam 2200457 450 001 996472065503316 005 20231110214919.0 010 $a981-19-1797-3 035 $a(MiAaPQ)EBC6965069 035 $a(Au-PeEL)EBL6965069 035 $a(CKB)21707968500041 035 $a(PPN)262168987 035 $a(EXLCZ)9921707968500041 100 $a20221123d2022 uy 0 101 0 $aeng 135 $aurcnu|||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 00$aPrivacy preservation in IoT $emachine learning approaches : a comprehensive survey and use cases /$fYouyang Qu [and three others] 210 1$aSingapore :$cSpringer,$d[2022] 210 4$dİ2022 215 $a1 online resource (127 pages) 225 1 $aSpringerBriefs in Computer Science 311 08$aPrint version: Qu, Youyang Privacy Preservation in IoT: Machine Learning Approaches Singapore : Springer,c2022 9789811917967 327 $aIntro -- Preface -- Acknowledgments -- Contents -- 1 Introduction -- 1.1 IoT Privacy Research Landscape -- 1.2 Machine Learning Driven Privacy Preservation Overview -- 1.3 Contribution of This Book -- 1.4 Book Overview -- 2 Current Methods of Privacy Protection in IoTs -- 2.1 Briefing of Privacy Preservation Study in IoTs -- 2.2 Cryptography-Based Methods in IoTs -- 2.3 Anonymity-Based and Clustering-Based Methods -- 2.4 Differential Privacy Based Methods -- 2.5 Machine Learning and AI Methods -- 2.5.1 Federated Learning -- 2.5.2 Generative Adversarial Network -- References -- 3 Decentralized Privacy Protection of IoTs Using Blockchain-Enabled Federated Learning -- 3.1 Overview -- 3.2 Related Work -- 3.3 Architecture of Blockchain-Enabled Federated Learning -- 3.3.1 Federated Learning in FL-Block -- 3.3.2 Blockchain in FL-Block -- 3.4 Decentralized Privacy Mechanism Based on FL-Block -- 3.4.1 Blocks Establishment -- 3.4.2 Blockchain Protocols Design -- 3.4.3 Discussion on Decentralized Privacy Protection Using Blockchain -- 3.5 System Analysis -- 3.5.1 Poisoning Attacks and Defence -- 3.5.2 Single-Epoch FL-Block Latency Model -- 3.5.3 Optimal Generation Rate of Blocks -- 3.6 Performance Evaluation -- 3.6.1 Simulation Environment Description -- 3.6.2 Global Models and Corresponding Updates -- 3.6.3 Evaluation on Convergence and Efficiency -- 3.6.4 Evaluation on Blockchain -- 3.6.5 Evaluation on Poisoning Attack Resistance -- 3.7 Summary and Future Work -- References -- 4 Personalized Privacy Protection of IoTs Using GAN-Enhanced Differential Privacy -- 4.1 Overview -- 4.2 Related Work -- 4.3 Generative Adversarial Nets Driven Personalized Differential Privacy -- 4.3.1 Extended Social Networks Graph Structure -- 4.3.2 GAN with a Differential Privacy Identifier -- 4.3.3 Mapping Function. 327 $a4.3.4 Opimized Trade-Off Between Personalized Privacy Protection and Optimized Data Utility -- 4.4 Attack Model and Mechanism Analysis -- 4.4.1 Collusion Attack -- 4.4.2 Attack Mechanism Analysis -- 4.5 System Analysis -- 4.6 Evaluation and Performance -- 4.6.1 Trajectory Generation Performance -- 4.6.2 Personalized Privacy Protection -- 4.6.3 Data Utility -- 4.6.4 Efficiency and Convergence -- 4.6.5 Further Discussion -- 4.7 Summary and Future Work -- References -- 5 Hybrid Privacy Protection of IoT Using Reinforcement Learning -- 5.1 Overview -- 5.2 Related Work -- 5.3 Hybrid Privacy Problem Formulation -- 5.3.1 Game-Based Markov Decision Process -- 5.3.2 Problem Formulation -- 5.4 System Modelling -- 5.4.1 Actions of the Adversary and User -- 5.4.2 System States and Transitions -- 5.4.3 Nash Equilibrium Under Game-Based MDP -- 5.5 System Analysis -- 5.5.1 Measurement of Overall Data Utility -- 5.5.2 Measurement of Privacy Loss -- 5.6 Markov Decision Process and Reinforcement Learning -- 5.6.1 Quick-Convergent Reinforcement Learning Algorithm -- 5.6.2 Best Strategy Generation with Limited Power -- 5.6.3 Best Strategy Generation with Unlimited Power -- 5.7 Performance Evaluation -- 5.7.1 Experiments Foundations -- 5.7.2 Data Utility Evaluations -- 5.7.3 Privacy Loss Evaluations -- 5.7.4 Convergence Speed -- 5.8 Summary and Future Work -- References -- 6 Future Research Directions -- 6.1 Trade-Off Optimization in IoTs -- 6.2 Privacy Preservation in Digital Twined IoTs -- 6.3 Personalized Consensus and Incentive Mechanisms for Blockchain-Enabled Federated Learning in IoTs -- 6.4 Privacy-Preserving Federated Learning in IoTs -- 6.5 Federated Generative Adversarial Network in IoTs -- 7 Summary and Outlook. 410 0$aSpringerBriefs in Computer Science 606 $aData privacy 606 $aInternet of things$xSecurity measures 615 0$aData privacy. 615 0$aInternet of things$xSecurity measures. 676 $a323.448 702 $aQu$b Youyang 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a996472065503316 996 $aPrivacy preservation in IoT$92965933 997 $aUNISA LEADER 03446nam 2200637z- 450 001 9910674007703321 005 20260129133427.0 010 $a3-0365-6148-X 035 $a(CKB)5470000001633490 035 $a(oapen)https://directory.doabooks.org/handle/20.500.12854/95833 035 $a(EXLCZ)995470000001633490 100 $a20202301d2022 |y 0 101 0 $aeng 135 $aurmn|---annan 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 00$aFuzzy Natural Logic in IFSA-EUSFLAT 2021 /$fedited by Antonin Dvorak and Vile?m Nova?k 210 $aBasel$cMDPI - Multidisciplinary Digital Publishing Institute$d2022 215 $a1 electronic resource (148 p.) 311 08$a3-0365-6147-1 330 $aThe present book contains five papers accepted and published in the Special Issue, ?Fuzzy Natural Logic in IFSA-EUSFLAT 2021?, of the journal Mathematics (MDPI). These papers are extended versions of the contributions presented in the conference ?The 19th World Congress of the International Fuzzy Systems Association and the 12th Conference of the European Society for Fuzzy Logic and Technology jointly with the AGOP, IJCRS, and FQAS conferences?, which took place in Bratislava (Slovakia) from September 19 to September 24, 2021. Fuzzy Natural Logic (FNL) is a system of mathematical fuzzy logic theories that enables us to model natural language terms and rules while accounting for their inherent vagueness and allows us to reason and argue using the tools developed in them. FNL includes, among others, the theory of evaluative linguistic expressions (e.g., small, very large, etc.), the theory of fuzzy and intermediate quantifiers (e.g., most, few, many, etc.), and the theory of fuzzy/linguistic IF?THEN rules and logical inference. The papers in this Special Issue use the various aspects and concepts of FNL mentioned above and apply them to a wide range of problems both theoretically and practically oriented. This book will be of interest for researchers working in the areas of fuzzy logic, applied linguistics, generalized quantifiers, and their applications. 606 $aResearch & information: general$2bicssc 606 $aMathematics & science$2bicssc 610 $afuzzy Peterson's syllogisms 610 $afuzzy intermediate quantifiers 610 $agraded Peterson's cube of opposition 610 $alinguistic universals 610 $alinguistic complexity 610 $aevaluative expressions 610 $afuzzy grammar 610 $alinguistic gradience 610 $alinguistic constraints 610 $agrammaticality 610 $asentiment analysis 610 $acloseness 610 $acloseness matrix 610 $acloseness space 610 $afunction similarity 610 $afuzzy partition 610 $afuzzy transform 610 $apreimage problem 610 $asingular value decomposition 610 $aevolving fuzzy neural network 610 $aor-neuron 610 $aauction fraud 610 $aknowledge extraction 615 7$aResearch & information: general 615 7$aMathematics & science 702 $aNova?k$b Vile?m$4edt 702 $aDvor?a?k$b Antoni?n$c(Mathematician)$4oth 702 $aNova?k$b Vile?m$f1951-$4oth 906 $aBOOK 912 $a9910674007703321 996 $aFuzzy Natural Logic in IFSA-EUSFLAT 2021$94533136 997 $aUNINA