| Description |
1 online resource (397 pages) |
| Contents |
Intro -- Contents -- Contributors -- 1 Big Data and Privacy: Challenges and Opportunities -- 1 Introduction -- 2 Book Outline -- References -- 2 AI and Security of Critical Infrastructure -- 1 Introduction: Towards Smart Urbanization -- 2 Applications of Smart Technologies -- 3 Cyber Physical Systems -- 3.1 CPS in Healthcare -- 3.2 CPS in Transportation -- 3.3 CPS in Manufacturing -- 3.4 CPS in Power Systems: The Smart Grid -- 4 Security Challenges in Cyber Physical Systems -- 4.1 Eavesdropping -- 4.2 Spoofing -- 4.3 Denial of Service (DoS) -- 4.4 Code Injection -- 4.5 Malware |
|
4.6 Control Hijacking -- 5 Defense Mechanisms -- 6 Applications of AI in Cyber Security -- 6.1 Traditional ML Algorithms for Cyber Security -- 6.1.1 Support Vector Machines (SVM) -- 6.1.2 K Nearest Neighbor (KNN) -- 6.1.3 Artificial Neural Network (ANN) -- 6.2 Deep Learning Algorithms -- 6.2.1 Deep Belief Networks (DBN) -- 6.2.2 Recurrent Neural Networks (RNN) -- 6.2.3 Convolutional Neural Networks (CNN) -- 6.2.4 Automatic Encoders -- 7 Deep Learning: Adapting to the Real World -- 8 Challenges of AI in Cyber Security -- 9 Conclusion -- References |
|
3 Industrial Big Data Analytics: Challenges and Opportunities -- 1 Introduction -- 2 Big Data Characteristics -- 3 Industrial Big Data Sources and Applications -- 3.1 Industrial Big Data Sources -- 3.1.1 Large-Scale Data Devices -- 3.1.2 Life-Cycle Production Data -- 3.1.3 Enterprise Operation Data -- 3.1.4 Manufacturing Value Chain -- 3.1.5 External Collaboration Data -- 3.2 Industrial Big Data Applications -- 3.2.1 Smart Factory Visibility -- 3.2.2 Machine Fleet Management -- 3.2.3 Proactive Maintenance -- 3.2.4 Service Innovation and Just in Time Smart Supply Chain |
|
4 Industrial Big Data Challenges and Issues -- 4.1 Lack of Largescale Spatiotemporal Database Representation -- 4.2 Lack of Effective and Efficient Online Machine Learning Algorithms -- 4.3 Lack of Whole Processes Lifecycle Data Management Systems -- 4.4 Lack of Data Visualization Systems -- 4.5 Lack in Data Confidentiality Mechanisms -- 5 Industrial Big Data Analytics: Solutions and Future Remarks -- 5.1 System Infrastructures -- 5.1.1 Data Capture -- 5.1.2 Data Storage -- 5.1.3 Data Process -- 5.2 Data Analytics Methods and Techniques -- 5.2.1 Descriptive Analytics -- 5.2.2 Predictive Analytics |
|
5.2.3 Prescriptive Analytics -- 6 Conclusion -- References -- 4 A Privacy Protection Key Agreement Protocol Based on ECC for Smart Grid -- 1 Introduction -- 2 Related Work -- 3 Contribution -- 4 Proposed Key Agreement and Authentication Scheme -- 4.1 Registration Phase -- 4.2 Key Agreement and Authentication Phase -- 5 Security and Performance Analyze of the Proposed Scheme -- 5.1 Security Review of the Proposed Method Against All Types of Network Attacks -- 5.2 Result and Formal Analyze -- 5.3 Performance Analysis -- 6 Conclusion -- References |
| Summary |
This handbook provides comprehensive knowledge and includes an overview of the current state-of-the-art of Big Data Privacy, with chapters written by international world leaders from academia and industry working in this field. The first part of this book offers a review of security challenges in critical infrastructure and offers methods that utilize acritical intelligence (AI) techniques to overcome those issues. It then focuses on big data security and privacy issues in relation to developments in the Industry 4.0. Internet of Things (IoT) devices are becoming a major source of security and privacy concern in big data platforms. Multiple solutions that leverage machine learning for addressing security and privacy issues in IoT environments are also discussed this handbook. The second part of this handbook is focused on privacy and security issues in different layers of big data systems. It discusses about methods for evaluating security and privacy of big data systems on network, application and physical layers. This handbook elaborates on existing methods to use data analytic and AI techniques at different layers of big data platforms to identify privacy and security attacks. The final part of this handbook is focused on analyzing cyber threats applicable to the big data environments. It offers an in-depth review of attacks applicable to big data platforms in smart grids, smart farming, FinTech, and health sectors. Multiple solutions are presented to detect, prevent and analyze cyber-attacks and assess the impact of malicious payloads to those environments. This handbook provides information for security and privacy experts in most areas of big data including; FinTech, Industry 4.0, Internet of Things, Smart Grids, Smart Farming and more. Experts working in big data, privacy, security, forensics, malware analysis, machine learning and data analysts will find this handbook useful as a reference. Researchers and advanced-level computer science students focused on computer systems, Internet of Things, Smart Grid, Smart Farming, Industry 4.0 and network analysts will also find this handbook useful as a reference |
| Notes |
5 Applications of Big Data Analytics and Machine Learning in the Internet of Things |
|
Print version record |
| Subject |
Computer security -- Handbooks, manuals, etc
|
|
Big data -- Security measures -- Handbooks, manuals, etc
|
|
Computer security
|
| Genre/Form |
Electronic books
|
|
handbooks.
|
|
Handbooks and manuals
|
|
Handbooks and manuals.
|
|
Guides et manuels.
|
| Form |
Electronic book
|
| Author |
Choo, Kim-Kwang Raymond
|
|
Dehghantanha, Ali
|
| ISBN |
9783030385576 |
|
3030385574 |
|
