Agbotiname Lucky Imoize is a Lecturer in the Department of Electrical and Electronics Engineering at the University of Lagos, Nigeria. He is a Fulbright Fellow, the Vice Chair of the IEEE Communication Society Nigeria chapter, and a Senior Member of IEEE. Dinh-Thuan Do, PhD, is an Assistant Professor with the School of Engineering at the University of Mount Union, USA. He is an editor of IEEE Transactions on Vehicular Technology and Computer Communications. He is a Senior Member of IEEE. Houbing Herbert Song, PhD, IEEE Fellow, is a Professor in the Department of Information Systems, and the Department of Computer Science and Electrical Engineering and Director of the Security and Optimization for Networked Globe Laboratory (SONG Lab) at the University of Maryland, Baltimore County. He is also Co-Editor-in-Chief of IEEE Transactions on Industrial Informatics.

• About the Editors xxiiiList of Contributors xxviiPreface xxxv1 Introduction to TinyML 1Francisca Onyiyechi Nwokoma, Chidi Ukamaka Betrand, Juliet Nnenna Odii, Euphemia Chioma Nwokorie, and Ikechukwu Ignatius Ayogu1.1 Introduction 11.2 Evolution of TinyML 61.3 Key Milestones and Current Trends 81.4 TinyML System Development 111.5 Challenges and Bottlenecks 171.6 Cost–Benefit Analysis 201.7 Key Findings 261.8 Limitations of TinyML 271.9 Conclusion 29References 302 Learning Panorama Under TinyML 35Ikechukwu Ignatius Ayogu, Euphemia Chioma Nwokorie, Juliet Nnenna Odii, Francisca Onyiyechi Nwokoma, and Chidi Ukamaka Betrand2.1 Introduction 352.2 Challenges and Opportunities for Improved TinyML Model Design 372.3 Frontiers in Model Optimization for TinyML 472.4 Learning Frameworks and Tools for TinyML Development 592.5 Frontiers for Algorithmic Innovations for TinyML 632.6 TinyML Development Process 682.7 Key Findings 692.8 Conclusion 70References 713 TinyML for Anomaly Detection 85Richard Govada Joshua, Peter Anuoluwapo Gbadega, Agbotiname Lucky Imoize, and Samuel Oluwatobi Tofade3.1 Introduction 853.2 Context and Literature Review 933.3 Lessons Learned 1493.4 Future Scope 1523.5 Conclusion 156References 1574 TinyML Power Consumption and Memory in IoT MCUs 163Peter Anuoluwapo Gbadega, Agbotiname Lucky Imoize, Richard Govada Joshua, and Samuel Oluwatobi Tofade4.1 Introduction 1634.2 Context and Literature Review 1714.3 Methodology 1744.4 Results and Discussion: Bibliometric Analysis 1844.5 Conclusion and Future Directions 198References 1995 Efficient Data Cleaning and Anomaly Detection in IoT Devices Using TinyCleanEDF 205Ilker Kara5.1 Introduction 2055.2 IoT and TinyCleanEDF 2065.3 The Importance of Data Cleaning in IoT Systems 2075.4 Anomaly Detection and Its Importance in IoT Systems 2085.5 Data Preprocessing and Cleaning Workflow 2095.6 Implementation Details 2135.7 Case Studies and Applications 2165.8 Future Directions 2195.9 Conclusion and Future Scope 221References 2226 TinyML Devices and Tools 225Abeeb Akorede Bello, Agbotiname Lucky Imoize, and Abiodun Temitope Odewale6.1 Introduction 2256.2 Related Work 2276.3 TinyML Devices 2346.4 TinyML Tools 2376.5 Deployment Procedure of TinyML 2416.6 Lesson Learned and Prospects 2506.7 Conclusion 253References 2547 Privacy-Preserving Techniques in TinyML for IoT 259Oleksandr Kuznetsov, Emanuele Frontoni, Kateryna Kuznetsova, Marco Arnesano, and Pavlo Usik7.1 Introduction 2597.2 Related Works 2617.3 Homomorphic Encryption in TinyML 2627.4 Differential Privacy for TinyML 2717.5 Secure Multi-Party Computation in TinyML 2777.6 Case Studies and Applications of Privacy-Preserving TinyML 2817.7 Discussion and Future Directions 2937.8 Conclusion 296Acknowledgment 296References 2968 Enhancing Cybersecurity in TinyML with Lightweight Cryptographic Algorithms 303Oleksandr Kuznetsov, Roman Minailenko, Aigul Shaikhanova, Yelyzaveta Kuznetsova, and Agbotiname Lucky Imoize8.1 Introduction 3038.2 Literature Review 3058.3 Lightweight Cryptographic Algorithms for TinyML 3068.4 Comparative Analysis of Lightweight Block Ciphers 3158.5 Comparative Analysis of Lightweight Hash Functions 3188.6 Comparative Analysis of Lightweight Stream Ciphers 3228.7 Implementation Strategies for Lightweight Cryptography in TinyML 3258.8 Conclusion 327Acknowledgment 328References 3299 Tiny Machine Learning for Enhanced Edge Intelligence 335Emmanuel Alozie, Agbotiname Lucky Imoize, Hawau I. Olagunju, Nasir Faruk, Salisu Garba, and Ayobami P. Olatunji9.1 Introduction 3359.2 Overview of Tiny Machine Learning (TinyML) 3379.3 TinyML as a Service (TMLaaS) Architecture 3499.4 Results and Discussion 3549.5 Open Challenges and Further Research Directions 3579.6 Conclusion 358References 35910 Advanced Security Schemes for TinyML Devices 367Wasswa Shafik and Mumin Adam10.1 Introduction 36710.2 Fundamentals of TinyML 36910.3 Privacy Concerns in TinyML 37410.4 Security and Privacy Solutions 37610.5 The Implementation of Novel Security Schemes for TinyML Applications 38410.6 Privacy-Enhancing Techniques for TinyML 38810.7 Future Directions of Security and Privacy in TinyML Devices 39110.8 Lessons Learned 39310.9 Limitations of this Study 39410.10 Conclusion 395References 39611 Robust Ground Truth Data Mining for Enhanced Privacy and Accuracy in Noisy TinyML Environments 403Yuichi Sei and Agbotiname Lucky Imoize11.1 Introduction 40311.2 Related Research Work 40611.3 Models 40811.4 Gdp 41211.5 Evaluation 41611.6 Discussion 42011.7 Conclusions 423References 42412 Security and Privacy of TinyML Devices 431Eftychia Mistillioglou, Evangelia Konstantopoulou, Nicolas Sklavos, and Andronikos Kyriakou12.1 Introduction 43112.2 Related Work 43312.3 Secure and Privacy-Aware Training of TinyML Models 43712.4 Implementation of Novel Security Schemes for TinyML Applications 45512.5 Lessons, Challenges, and Future Directions 46312.6 Conclusions and Outlook 464References 46513 Semantic Management of TinyML for Industrial Application 469Kinzah Noor, Hasnain Ahmad, and Agbotiname Lucky Imoize13.1 Introduction 46913.2 Introduction to TinyML 47213.3 Recent Advances in TinyML 47713.4 Methodology 48813.5 Results and Discussion 49513.6 Conclusions and Future Scope 498References 49814 Fight Poison with Poison: Tiny Machine Learning Resilience Against Poisoning Attacks 503Tomoki Chiba, Yasuyuki Tahara, Akihiko Ohsuga, Agbotiname Lucky Imoize, and Yuichi Sei14.1 Introduction 50314.2 Problem Definition 50514.3 Related Work 50714.4 Proposed Method 51214.5 Evaluation Experiment 52314.6 Discussion 54114.7 Conclusion 543References 54415 TinyML for Real-Time Medical Image Classification and Diagnosis 549Jelil O. Agbo-Ajala, Lateef A. Akinyemi, Olufisayo S. Ekundayo, and Ernest Mnkandla15.1 Introduction 54915.2 Literature Review 55115.3 Methodology 56615.4 Results and Discussion 56715.5 Conclusion 578References 57816 Biometric Authentication in TinyML: Opportunities and Challenges 587Oleksandr Kuznetsov, Emanuele Frontoni, Marco Arnesano, Oleksii Smirnov, and Boris Khruskov16.1 Introduction 58716.2 Related Work 58916.3 Overview of Biometric Authentication Techniques 59116.4 Comparative Analysis of Biometric Authentication Methods 60916.5 Adapting Biometric Techniques for TinyML Systems 61516.6 Discussion and Future Directions 62516.7 Conclusion 628Acknowledgment 628References 62917 Secure Deployment of TinyML Applications: Strategies and Practices 635Oleksandr Kuznetsov, Sergii Kavun, and Gulvira Bekeshova17.1 Introduction 63517.2 Related Work 63617.3 Security Architectures for TinyML Deployments 63817.4 Secure Bootstrapping and Key Management 64317.5 Secure Communication Protocols for TinyML 64617.6 Data Privacy in TinyML Applications 65017.7 Future Directions and Emerging Technologies 65217.8 Conclusion 655Acknowledgment 657References 65718 TinyML for Environmental Applications 665Duy Nam Khanh Vu and Anh Khoa Dang18.1 Introduction 66518.2 Related Work 66718.3 Methodology 66918.4 Case Study: New Insights on Air Writing from Pławiak and Alblehai 68918.5 Results and Discussion 69218.6 Conclusion and Future Scope 697References 69719 Benchmarking TinyML Encrypted Federated Learning with Secret Sharing in Medical Computer Vision 701Ruduan B. F. Plug, Putu H. P. Jati, Samson Y. Amare, and Mirjam van Reisen19.1 Introduction 70119.2 Related Work 70219.3 Methodology 70319.4 Results 71119.5 Conclusion 715References 716Index 721

Agbotiname Lucky Imoize is a Lecturer in the Department of Electrical and Electronics Engineering at the University of Lagos, Nigeria. He is a Fulbright Fellow, the Vice Chair of the IEEE Communication Society Nigeria chapter, and a Senior Member of IEEE. Dinh-Thuan Do, PhD, is an Assistant Professor with the School of Engineering at the University of Mount Union, USA. He is an editor of IEEE Transactions on Vehicular Technology and Computer Communications. He is a Senior Member of IEEE. Houbing Herbert Song, PhD, IEEE Fellow, is a Professor in the Department of Information Systems, and the Department of Computer Science and Electrical Engineering and Director of the Security and Optimization for Networked Globe Laboratory (SONG Lab) at the University of Maryland, Baltimore County. He is also Co-Editor-in-Chief of IEEE Transactions on Industrial Informatics.

• About the Editors xxiiiList of Contributors xxviiPreface xxxv1 Introduction to TinyML 1Francisca Onyiyechi Nwokoma, Chidi Ukamaka Betrand, Juliet Nnenna Odii, Euphemia Chioma Nwokorie, and Ikechukwu Ignatius Ayogu1.1 Introduction 11.2 Evolution of TinyML 61.3 Key Milestones and Current Trends 81.4 TinyML System Development 111.5 Challenges and Bottlenecks 171.6 Cost–Benefit Analysis 201.7 Key Findings 261.8 Limitations of TinyML 271.9 Conclusion 29References 302 Learning Panorama Under TinyML 35Ikechukwu Ignatius Ayogu, Euphemia Chioma Nwokorie, Juliet Nnenna Odii, Francisca Onyiyechi Nwokoma, and Chidi Ukamaka Betrand2.1 Introduction 352.2 Challenges and Opportunities for Improved TinyML Model Design 372.3 Frontiers in Model Optimization for TinyML 472.4 Learning Frameworks and Tools for TinyML Development 592.5 Frontiers for Algorithmic Innovations for TinyML 632.6 TinyML Development Process 682.7 Key Findings 692.8 Conclusion 70References 713 TinyML for Anomaly Detection 85Richard Govada Joshua, Peter Anuoluwapo Gbadega, Agbotiname Lucky Imoize, and Samuel Oluwatobi Tofade3.1 Introduction 853.2 Context and Literature Review 933.3 Lessons Learned 1493.4 Future Scope 1523.5 Conclusion 156References 1574 TinyML Power Consumption and Memory in IoT MCUs 163Peter Anuoluwapo Gbadega, Agbotiname Lucky Imoize, Richard Govada Joshua, and Samuel Oluwatobi Tofade4.1 Introduction 1634.2 Context and Literature Review 1714.3 Methodology 1744.4 Results and Discussion: Bibliometric Analysis 1844.5 Conclusion and Future Directions 198References 1995 Efficient Data Cleaning and Anomaly Detection in IoT Devices Using TinyCleanEDF 205Ilker Kara5.1 Introduction 2055.2 IoT and TinyCleanEDF 2065.3 The Importance of Data Cleaning in IoT Systems 2075.4 Anomaly Detection and Its Importance in IoT Systems 2085.5 Data Preprocessing and Cleaning Workflow 2095.6 Implementation Details 2135.7 Case Studies and Applications 2165.8 Future Directions 2195.9 Conclusion and Future Scope 221References 2226 TinyML Devices and Tools 225Abeeb Akorede Bello, Agbotiname Lucky Imoize, and Abiodun Temitope Odewale6.1 Introduction 2256.2 Related Work 2276.3 TinyML Devices 2346.4 TinyML Tools 2376.5 Deployment Procedure of TinyML 2416.6 Lesson Learned and Prospects 2506.7 Conclusion 253References 2547 Privacy-Preserving Techniques in TinyML for IoT 259Oleksandr Kuznetsov, Emanuele Frontoni, Kateryna Kuznetsova, Marco Arnesano, and Pavlo Usik7.1 Introduction 2597.2 Related Works 2617.3 Homomorphic Encryption in TinyML 2627.4 Differential Privacy for TinyML 2717.5 Secure Multi-Party Computation in TinyML 2777.6 Case Studies and Applications of Privacy-Preserving TinyML 2817.7 Discussion and Future Directions 2937.8 Conclusion 296Acknowledgment 296References 2968 Enhancing Cybersecurity in TinyML with Lightweight Cryptographic Algorithms 303Oleksandr Kuznetsov, Roman Minailenko, Aigul Shaikhanova, Yelyzaveta Kuznetsova, and Agbotiname Lucky Imoize8.1 Introduction 3038.2 Literature Review 3058.3 Lightweight Cryptographic Algorithms for TinyML 3068.4 Comparative Analysis of Lightweight Block Ciphers 3158.5 Comparative Analysis of Lightweight Hash Functions 3188.6 Comparative Analysis of Lightweight Stream Ciphers 3228.7 Implementation Strategies for Lightweight Cryptography in TinyML 3258.8 Conclusion 327Acknowledgment 328References 3299 Tiny Machine Learning for Enhanced Edge Intelligence 335Emmanuel Alozie, Agbotiname Lucky Imoize, Hawau I. Olagunju, Nasir Faruk, Salisu Garba, and Ayobami P. Olatunji9.1 Introduction 3359.2 Overview of Tiny Machine Learning (TinyML) 3379.3 TinyML as a Service (TMLaaS) Architecture 3499.4 Results and Discussion 3549.5 Open Challenges and Further Research Directions 3579.6 Conclusion 358References 35910 Advanced Security Schemes for TinyML Devices 367Wasswa Shafik and Mumin Adam10.1 Introduction 36710.2 Fundamentals of TinyML 36910.3 Privacy Concerns in TinyML 37410.4 Security and Privacy Solutions 37610.5 The Implementation of Novel Security Schemes for TinyML Applications 38410.6 Privacy-Enhancing Techniques for TinyML 38810.7 Future Directions of Security and Privacy in TinyML Devices 39110.8 Lessons Learned 39310.9 Limitations of this Study 39410.10 Conclusion 395References 39611 Robust Ground Truth Data Mining for Enhanced Privacy and Accuracy in Noisy TinyML Environments 403Yuichi Sei and Agbotiname Lucky Imoize11.1 Introduction 40311.2 Related Research Work 40611.3 Models 40811.4 Gdp 41211.5 Evaluation 41611.6 Discussion 42011.7 Conclusions 423References 42412 Security and Privacy of TinyML Devices 431Eftychia Mistillioglou, Evangelia Konstantopoulou, Nicolas Sklavos, and Andronikos Kyriakou12.1 Introduction 43112.2 Related Work 43312.3 Secure and Privacy-Aware Training of TinyML Models 43712.4 Implementation of Novel Security Schemes for TinyML Applications 45512.5 Lessons, Challenges, and Future Directions 46312.6 Conclusions and Outlook 464References 46513 Semantic Management of TinyML for Industrial Application 469Kinzah Noor, Hasnain Ahmad, and Agbotiname Lucky Imoize13.1 Introduction 46913.2 Introduction to TinyML 47213.3 Recent Advances in TinyML 47713.4 Methodology 48813.5 Results and Discussion 49513.6 Conclusions and Future Scope 498References 49814 Fight Poison with Poison: Tiny Machine Learning Resilience Against Poisoning Attacks 503Tomoki Chiba, Yasuyuki Tahara, Akihiko Ohsuga, Agbotiname Lucky Imoize, and Yuichi Sei14.1 Introduction 50314.2 Problem Definition 50514.3 Related Work 50714.4 Proposed Method 51214.5 Evaluation Experiment 52314.6 Discussion 54114.7 Conclusion 543References 54415 TinyML for Real-Time Medical Image Classification and Diagnosis 549Jelil O. Agbo-Ajala, Lateef A. Akinyemi, Olufisayo S. Ekundayo, and Ernest Mnkandla15.1 Introduction 54915.2 Literature Review 55115.3 Methodology 56615.4 Results and Discussion 56715.5 Conclusion 578References 57816 Biometric Authentication in TinyML: Opportunities and Challenges 587Oleksandr Kuznetsov, Emanuele Frontoni, Marco Arnesano, Oleksii Smirnov, and Boris Khruskov16.1 Introduction 58716.2 Related Work 58916.3 Overview of Biometric Authentication Techniques 59116.4 Comparative Analysis of Biometric Authentication Methods 60916.5 Adapting Biometric Techniques for TinyML Systems 61516.6 Discussion and Future Directions 62516.7 Conclusion 628Acknowledgment 628References 62917 Secure Deployment of TinyML Applications: Strategies and Practices 635Oleksandr Kuznetsov, Sergii Kavun, and Gulvira Bekeshova17.1 Introduction 63517.2 Related Work 63617.3 Security Architectures for TinyML Deployments 63817.4 Secure Bootstrapping and Key Management 64317.5 Secure Communication Protocols for TinyML 64617.6 Data Privacy in TinyML Applications 65017.7 Future Directions and Emerging Technologies 65217.8 Conclusion 655Acknowledgment 657References 65718 TinyML for Environmental Applications 665Duy Nam Khanh Vu and Anh Khoa Dang18.1 Introduction 66518.2 Related Work 66718.3 Methodology 66918.4 Case Study: New Insights on Air Writing from Pławiak and Alblehai 68918.5 Results and Discussion 69218.6 Conclusion and Future Scope 697References 69719 Benchmarking TinyML Encrypted Federated Learning with Secret Sharing in Medical Computer Vision 701Ruduan B. F. Plug, Putu H. P. Jati, Samson Y. Amare, and Mirjam van Reisen19.1 Introduction 70119.2 Related Work 70219.3 Methodology 70319.4 Results 71119.5 Conclusion 715References 716Index 721

Agbotiname Lucky Imoize is a Lecturer in the Department of Electrical and Electronics Engineering at the University of Lagos, Nigeria. He is a Fulbright Fellow, the Vice Chair of the IEEE Communication Society Nigeria chapter, and a Senior Member of IEEE. Dinh-Thuan Do, PhD, is an Assistant Professor with the School of Engineering at the University of Mount Union, USA. He is an editor of IEEE Transactions on Vehicular Technology and Computer Communications. He is a Senior Member of IEEE. Houbing Herbert Song, PhD, IEEE Fellow, is a Professor in the Department of Information Systems, and the Department of Computer Science and Electrical Engineering and Director of the Security and Optimization for Networked Globe Laboratory (SONG Lab) at the University of Maryland, Baltimore County. He is also Co-Editor-in-Chief of IEEE Transactions on Industrial Informatics.

• About the Editors xxiiiList of Contributors xxviiPreface xxxv1 Introduction to TinyML 1Francisca Onyiyechi Nwokoma, Chidi Ukamaka Betrand, Juliet Nnenna Odii, Euphemia Chioma Nwokorie, and Ikechukwu Ignatius Ayogu1.1 Introduction 11.2 Evolution of TinyML 61.3 Key Milestones and Current Trends 81.4 TinyML System Development 111.5 Challenges and Bottlenecks 171.6 Cost–Benefit Analysis 201.7 Key Findings 261.8 Limitations of TinyML 271.9 Conclusion 29References 302 Learning Panorama Under TinyML 35Ikechukwu Ignatius Ayogu, Euphemia Chioma Nwokorie, Juliet Nnenna Odii, Francisca Onyiyechi Nwokoma, and Chidi Ukamaka Betrand2.1 Introduction 352.2 Challenges and Opportunities for Improved TinyML Model Design 372.3 Frontiers in Model Optimization for TinyML 472.4 Learning Frameworks and Tools for TinyML Development 592.5 Frontiers for Algorithmic Innovations for TinyML 632.6 TinyML Development Process 682.7 Key Findings 692.8 Conclusion 70References 713 TinyML for Anomaly Detection 85Richard Govada Joshua, Peter Anuoluwapo Gbadega, Agbotiname Lucky Imoize, and Samuel Oluwatobi Tofade3.1 Introduction 853.2 Context and Literature Review 933.3 Lessons Learned 1493.4 Future Scope 1523.5 Conclusion 156References 1574 TinyML Power Consumption and Memory in IoT MCUs 163Peter Anuoluwapo Gbadega, Agbotiname Lucky Imoize, Richard Govada Joshua, and Samuel Oluwatobi Tofade4.1 Introduction 1634.2 Context and Literature Review 1714.3 Methodology 1744.4 Results and Discussion: Bibliometric Analysis 1844.5 Conclusion and Future Directions 198References 1995 Efficient Data Cleaning and Anomaly Detection in IoT Devices Using TinyCleanEDF 205Ilker Kara5.1 Introduction 2055.2 IoT and TinyCleanEDF 2065.3 The Importance of Data Cleaning in IoT Systems 2075.4 Anomaly Detection and Its Importance in IoT Systems 2085.5 Data Preprocessing and Cleaning Workflow 2095.6 Implementation Details 2135.7 Case Studies and Applications 2165.8 Future Directions 2195.9 Conclusion and Future Scope 221References 2226 TinyML Devices and Tools 225Abeeb Akorede Bello, Agbotiname Lucky Imoize, and Abiodun Temitope Odewale6.1 Introduction 2256.2 Related Work 2276.3 TinyML Devices 2346.4 TinyML Tools 2376.5 Deployment Procedure of TinyML 2416.6 Lesson Learned and Prospects 2506.7 Conclusion 253References 2547 Privacy-Preserving Techniques in TinyML for IoT 259Oleksandr Kuznetsov, Emanuele Frontoni, Kateryna Kuznetsova, Marco Arnesano, and Pavlo Usik7.1 Introduction 2597.2 Related Works 2617.3 Homomorphic Encryption in TinyML 2627.4 Differential Privacy for TinyML 2717.5 Secure Multi-Party Computation in TinyML 2777.6 Case Studies and Applications of Privacy-Preserving TinyML 2817.7 Discussion and Future Directions 2937.8 Conclusion 296Acknowledgment 296References 2968 Enhancing Cybersecurity in TinyML with Lightweight Cryptographic Algorithms 303Oleksandr Kuznetsov, Roman Minailenko, Aigul Shaikhanova, Yelyzaveta Kuznetsova, and Agbotiname Lucky Imoize8.1 Introduction 3038.2 Literature Review 3058.3 Lightweight Cryptographic Algorithms for TinyML 3068.4 Comparative Analysis of Lightweight Block Ciphers 3158.5 Comparative Analysis of Lightweight Hash Functions 3188.6 Comparative Analysis of Lightweight Stream Ciphers 3228.7 Implementation Strategies for Lightweight Cryptography in TinyML 3258.8 Conclusion 327Acknowledgment 328References 3299 Tiny Machine Learning for Enhanced Edge Intelligence 335Emmanuel Alozie, Agbotiname Lucky Imoize, Hawau I. Olagunju, Nasir Faruk, Salisu Garba, and Ayobami P. Olatunji9.1 Introduction 3359.2 Overview of Tiny Machine Learning (TinyML) 3379.3 TinyML as a Service (TMLaaS) Architecture 3499.4 Results and Discussion 3549.5 Open Challenges and Further Research Directions 3579.6 Conclusion 358References 35910 Advanced Security Schemes for TinyML Devices 367Wasswa Shafik and Mumin Adam10.1 Introduction 36710.2 Fundamentals of TinyML 36910.3 Privacy Concerns in TinyML 37410.4 Security and Privacy Solutions 37610.5 The Implementation of Novel Security Schemes for TinyML Applications 38410.6 Privacy-Enhancing Techniques for TinyML 38810.7 Future Directions of Security and Privacy in TinyML Devices 39110.8 Lessons Learned 39310.9 Limitations of this Study 39410.10 Conclusion 395References 39611 Robust Ground Truth Data Mining for Enhanced Privacy and Accuracy in Noisy TinyML Environments 403Yuichi Sei and Agbotiname Lucky Imoize11.1 Introduction 40311.2 Related Research Work 40611.3 Models 40811.4 Gdp 41211.5 Evaluation 41611.6 Discussion 42011.7 Conclusions 423References 42412 Security and Privacy of TinyML Devices 431Eftychia Mistillioglou, Evangelia Konstantopoulou, Nicolas Sklavos, and Andronikos Kyriakou12.1 Introduction 43112.2 Related Work 43312.3 Secure and Privacy-Aware Training of TinyML Models 43712.4 Implementation of Novel Security Schemes for TinyML Applications 45512.5 Lessons, Challenges, and Future Directions 46312.6 Conclusions and Outlook 464References 46513 Semantic Management of TinyML for Industrial Application 469Kinzah Noor, Hasnain Ahmad, and Agbotiname Lucky Imoize13.1 Introduction 46913.2 Introduction to TinyML 47213.3 Recent Advances in TinyML 47713.4 Methodology 48813.5 Results and Discussion 49513.6 Conclusions and Future Scope 498References 49814 Fight Poison with Poison: Tiny Machine Learning Resilience Against Poisoning Attacks 503Tomoki Chiba, Yasuyuki Tahara, Akihiko Ohsuga, Agbotiname Lucky Imoize, and Yuichi Sei14.1 Introduction 50314.2 Problem Definition 50514.3 Related Work 50714.4 Proposed Method 51214.5 Evaluation Experiment 52314.6 Discussion 54114.7 Conclusion 543References 54415 TinyML for Real-Time Medical Image Classification and Diagnosis 549Jelil O. Agbo-Ajala, Lateef A. Akinyemi, Olufisayo S. Ekundayo, and Ernest Mnkandla15.1 Introduction 54915.2 Literature Review 55115.3 Methodology 56615.4 Results and Discussion 56715.5 Conclusion 578References 57816 Biometric Authentication in TinyML: Opportunities and Challenges 587Oleksandr Kuznetsov, Emanuele Frontoni, Marco Arnesano, Oleksii Smirnov, and Boris Khruskov16.1 Introduction 58716.2 Related Work 58916.3 Overview of Biometric Authentication Techniques 59116.4 Comparative Analysis of Biometric Authentication Methods 60916.5 Adapting Biometric Techniques for TinyML Systems 61516.6 Discussion and Future Directions 62516.7 Conclusion 628Acknowledgment 628References 62917 Secure Deployment of TinyML Applications: Strategies and Practices 635Oleksandr Kuznetsov, Sergii Kavun, and Gulvira Bekeshova17.1 Introduction 63517.2 Related Work 63617.3 Security Architectures for TinyML Deployments 63817.4 Secure Bootstrapping and Key Management 64317.5 Secure Communication Protocols for TinyML 64617.6 Data Privacy in TinyML Applications 65017.7 Future Directions and Emerging Technologies 65217.8 Conclusion 655Acknowledgment 657References 65718 TinyML for Environmental Applications 665Duy Nam Khanh Vu and Anh Khoa Dang18.1 Introduction 66518.2 Related Work 66718.3 Methodology 66918.4 Case Study: New Insights on Air Writing from Pławiak and Alblehai 68918.5 Results and Discussion 69218.6 Conclusion and Future Scope 697References 69719 Benchmarking TinyML Encrypted Federated Learning with Secret Sharing in Medical Computer Vision 701Ruduan B. F. Plug, Putu H. P. Jati, Samson Y. Amare, and Mirjam van Reisen19.1 Introduction 70119.2 Related Work 70219.3 Methodology 70319.4 Results 71119.5 Conclusion 715References 716Index 721