LIMITED OFFER
Save 50% on book bundles
Immediately download your ebook while waiting for your print delivery. No promo code needed.
Deep Learning Empowered Security in Cyber physical systems
- 1st Edition - December 1, 2029
- Editors: Danda B. Rawat, Aaisha Makkar, Pushpita Chatterjee, Uttam Ghosh
- Language: English
- eBook ISBN:9 7 8 - 0 - 3 2 3 - 9 0 6 7 1 - 5
Deep Learning Empowered Security in Cyber Physical Systems presents the conceptual and core technical aspects that provide an insight into the latest research trends and relevant… Read more
Purchase options
Institutional subscription on ScienceDirect
Request a sales quoteDeep Learning Empowered Security in Cyber Physical Systems presents the conceptual and core technical aspects that provide an insight into the latest research trends and relevant theoretical framework in the field of CPS and its security.
User’s interest is in learning the different methods by which IoT data can be secured. The interesting fact is that the Artificial Intelligence (AI) plays a major role in it. Thus, such techniques are explored in this book. The approach followed is that the practical knowledge is delivered along with the theoretical concepts. In this era, every CPS requires the system which should be secure data.
This book serves as a basis for securing the data of every CPS. As the various paradigms such as CPS, deep learning is explained in detail. No other book integrates securing cyber physical systems using deep learning methods.
User’s interest is in learning the different methods by which IoT data can be secured. The interesting fact is that the Artificial Intelligence (AI) plays a major role in it. Thus, such techniques are explored in this book. The approach followed is that the practical knowledge is delivered along with the theoretical concepts. In this era, every CPS requires the system which should be secure data.
This book serves as a basis for securing the data of every CPS. As the various paradigms such as CPS, deep learning is explained in detail. No other book integrates securing cyber physical systems using deep learning methods.
- Illustrates deep learning techniques in detail along with its application in IoT devices
- Discusses multiple deep learning techniques considering all the IoT applications with the code/implementation and examples
- Presents the conceptual and core technical aspects that provide an insight into the latest research trends and relevant theoretical framework in the field of CPS and its security
Undergraduate, Graduate, Industrial Professional, Researchers mainly the audience working in Data Science, AI, ML, Networking, domain (Computer Science, Electronics, IT Engineering field)
Part 1: Security and threats in CPS
1. Cyber Physical systems
1.1 Security Objectives for Cyber-Physical Systems
1.2 CPS Attacks and Threats
1.3 Eavesdropping
1.4 Compromised-Key Attack
1.5 Man-in-the-Middle Attack
1.6 Denial-of-Service (DoS) Attack
1.7 CPS Defense Mechanisms
1.8 Cybersecurity and Privacy in Cyber-Physical Systems
2. Vulnerabilities in CPSs
2.1 Vulnerabilities of Platform
2.2 Vulnerabilities Encountered in the Network Layer
2.3 Vulnerabilities in Management and Policy
2.4 Reasons/Causes for Vulnerability in CPS
2.5 Communications Vulnerabilities
2.6 Smart Grid Security
2.7 Cyberattacks in Smart Grids
2.8 Vulnerability Analysis
3. CPS Security Perspectives
3.1 Intrusion Detection Systems
3.2 Estimation of Consequences of Cyber Attacks
3.3 Modeling of CPS Attacks
3.4 CPS Attacks Detection
3.5 Development of Security Architecture
3.6 CPS Architecture and Attacks
3.7 Attacks at the Perception Layer
3.8 Attacks at the Transmission Layer
3.9 Attacks at the Application Layer
3.10 Attack Mitigation Strategy
3.11 Risk Assessment for CPS
3.12 Single-Layer Solutions for CPS
3.13 Multilayer Solutions for CPS
4. Embedded Systems Security for Cyber-Physical Systems
4.1 Embedded Systems in CPS
4.2 Transformation
4.3 Modeling and Design
4.4 Tools and Languages
4.5 Challenges in Transformation
4.6 Security of Embedded Systems in CPS
4.7 Transformation of Security
4.8 Smart Grids Security
4.9 Interconnecting the Internet and Embedded Systems
5. Distributed Control Systems Security for CPS
5.1 Distributed Control Systems
5.2 Design and Architecture
5.3 Modeling and Framework for DCS and CPS
5.4 Management of DCS 5.5 Security and Risk
5.6 Security Issues
5.7 Security Measures
Part 2: Challenges and Frameworks of CPS
1. Complex, Resilient and Smart Systems
1.1 Challenges and Opportunities for Model-Based Security Risk Assessment of Cyber-Physical Systems
1.2 A Comprehensive Framework for the Security Risk Management of Cyber-Physical Systems
2. Evaluation Methodologies and Tools
2.1 Supporting Cybersecurity Compliance Assessment of Industrial Automation and Control System Components
2.2 Quantitative Evaluation of the Efficacy of Defence-in-Depth in Critical Infrastructures
2.3 A Model-Driven and Generative Approach to Holistic Security
3. The Safety and Security Landscape
3.1 Introduction
3.2 Cyber-Physical Systems Are Shockingly Easy to Attack
3.3 Cyber-Physical System Disruptions Require Extensive and Lengthy Repairs
3.4 Privacy Is a Critical Requirement
4. Risk Management
4.1 Fault Models and Hazard Analysis
4.2 Attack Models and Attack Analysis
4.3 Standards and Certification
4.4 Quality Management Systems
4.5 Safety Design Processes
5. Threats and Threat Analysis
5.1 Vulnerabilities, Hazards, and Threats
5.2 Compound Threats
5.3 Threat Analysis Models
5.4 Characteristics of Vulnerabilities and Threats
5.5 Improper Authorization Threats
6. False Data Injection Attacks
6.1 Introduction
6.2 Vulnerability Analysis
6.3 Dynamic Monitoring
Part 3: Deep Learning
1. Deep learning models
1.1 Feed-Forward Neural Networks
1.2 Perceptron
1.3 Multi-Layer Neural Network
1.4 Learning in Feed-Forward Neural Networks
1.5 Convolutional Neural Networks
1.6 Convolution and Pooling Layer
1.7 Computing Gradients
1.8 Deep Models
1.9 Vanishing Gradient Problem
1.10 Deep Neural Networks
1.11 Auto-Encoder
1.12 Stacked Auto-Encoder
1.13 Deep Generative Models
1.14 Restricted Boltzmann Machine
1.15 Deep Belief Network
1.16 Deep Boltzmann Machine
1.17 Open-Source Tools for Deep Learning
2. Deep understanding of models
2.1 How do We Train Deep Architectures?
2.2 Intermediate Representations: Sharing Features and Abstractions Across Tasks
2.3 Desiderata for Learning AI
2.4 Computational Complexity
2.5 Informal Arguments
2.6 The Limits of Matching Local Templates
2.7 Learning Distributed Representations
3. Energy-Based Models and Boltzmann Machines
3.1 Energy-Based Models and Products of Experts
3.2 Boltzmann Machines
3.3 Restricted Boltzmann Machines
3.4 Contrastive Divergence
4. Greedy Layer-Wise Training of Deep Architectures
4.1 Layer-Wise Training of Deep Belief Networks
4.2 Training Stacked Auto-Encoders
4.3 Semi-Supervised and Partially Supervised Training
5. Variants of RBMs and Auto-Encoders
5.1 Sparse Representations in Auto-Encoder and RBMs
5.2 Denoising Auto-Encoders
5.3 Lateral Connections
5.4 Conditional RBMs and Temporal RBMs
5.5 Factored RBMs
5.6 Generalizing RBMs and Contrastive Divergence
6. Stochastic Variational Bounds for Joint Optimization of DBN Layers
6.1 Unfolding RBMs into Infinite Directed Belief Networks
6.2 Variational Justification of Greedy Layer-wise Training
6.3 Joint Unsupervised Training of All the Layers
7. Looking Forward
7.1 Global Optimization Strategies
7.2 Why Unsupervised Learning is Important
7.3 Open Questions
1. Cyber Physical systems
1.1 Security Objectives for Cyber-Physical Systems
1.2 CPS Attacks and Threats
1.3 Eavesdropping
1.4 Compromised-Key Attack
1.5 Man-in-the-Middle Attack
1.6 Denial-of-Service (DoS) Attack
1.7 CPS Defense Mechanisms
1.8 Cybersecurity and Privacy in Cyber-Physical Systems
2. Vulnerabilities in CPSs
2.1 Vulnerabilities of Platform
2.2 Vulnerabilities Encountered in the Network Layer
2.3 Vulnerabilities in Management and Policy
2.4 Reasons/Causes for Vulnerability in CPS
2.5 Communications Vulnerabilities
2.6 Smart Grid Security
2.7 Cyberattacks in Smart Grids
2.8 Vulnerability Analysis
3. CPS Security Perspectives
3.1 Intrusion Detection Systems
3.2 Estimation of Consequences of Cyber Attacks
3.3 Modeling of CPS Attacks
3.4 CPS Attacks Detection
3.5 Development of Security Architecture
3.6 CPS Architecture and Attacks
3.7 Attacks at the Perception Layer
3.8 Attacks at the Transmission Layer
3.9 Attacks at the Application Layer
3.10 Attack Mitigation Strategy
3.11 Risk Assessment for CPS
3.12 Single-Layer Solutions for CPS
3.13 Multilayer Solutions for CPS
4. Embedded Systems Security for Cyber-Physical Systems
4.1 Embedded Systems in CPS
4.2 Transformation
4.3 Modeling and Design
4.4 Tools and Languages
4.5 Challenges in Transformation
4.6 Security of Embedded Systems in CPS
4.7 Transformation of Security
4.8 Smart Grids Security
4.9 Interconnecting the Internet and Embedded Systems
5. Distributed Control Systems Security for CPS
5.1 Distributed Control Systems
5.2 Design and Architecture
5.3 Modeling and Framework for DCS and CPS
5.4 Management of DCS 5.5 Security and Risk
5.6 Security Issues
5.7 Security Measures
Part 2: Challenges and Frameworks of CPS
1. Complex, Resilient and Smart Systems
1.1 Challenges and Opportunities for Model-Based Security Risk Assessment of Cyber-Physical Systems
1.2 A Comprehensive Framework for the Security Risk Management of Cyber-Physical Systems
2. Evaluation Methodologies and Tools
2.1 Supporting Cybersecurity Compliance Assessment of Industrial Automation and Control System Components
2.2 Quantitative Evaluation of the Efficacy of Defence-in-Depth in Critical Infrastructures
2.3 A Model-Driven and Generative Approach to Holistic Security
3. The Safety and Security Landscape
3.1 Introduction
3.2 Cyber-Physical Systems Are Shockingly Easy to Attack
3.3 Cyber-Physical System Disruptions Require Extensive and Lengthy Repairs
3.4 Privacy Is a Critical Requirement
4. Risk Management
4.1 Fault Models and Hazard Analysis
4.2 Attack Models and Attack Analysis
4.3 Standards and Certification
4.4 Quality Management Systems
4.5 Safety Design Processes
5. Threats and Threat Analysis
5.1 Vulnerabilities, Hazards, and Threats
5.2 Compound Threats
5.3 Threat Analysis Models
5.4 Characteristics of Vulnerabilities and Threats
5.5 Improper Authorization Threats
6. False Data Injection Attacks
6.1 Introduction
6.2 Vulnerability Analysis
6.3 Dynamic Monitoring
Part 3: Deep Learning
1. Deep learning models
1.1 Feed-Forward Neural Networks
1.2 Perceptron
1.3 Multi-Layer Neural Network
1.4 Learning in Feed-Forward Neural Networks
1.5 Convolutional Neural Networks
1.6 Convolution and Pooling Layer
1.7 Computing Gradients
1.8 Deep Models
1.9 Vanishing Gradient Problem
1.10 Deep Neural Networks
1.11 Auto-Encoder
1.12 Stacked Auto-Encoder
1.13 Deep Generative Models
1.14 Restricted Boltzmann Machine
1.15 Deep Belief Network
1.16 Deep Boltzmann Machine
1.17 Open-Source Tools for Deep Learning
2. Deep understanding of models
2.1 How do We Train Deep Architectures?
2.2 Intermediate Representations: Sharing Features and Abstractions Across Tasks
2.3 Desiderata for Learning AI
2.4 Computational Complexity
2.5 Informal Arguments
2.6 The Limits of Matching Local Templates
2.7 Learning Distributed Representations
3. Energy-Based Models and Boltzmann Machines
3.1 Energy-Based Models and Products of Experts
3.2 Boltzmann Machines
3.3 Restricted Boltzmann Machines
3.4 Contrastive Divergence
4. Greedy Layer-Wise Training of Deep Architectures
4.1 Layer-Wise Training of Deep Belief Networks
4.2 Training Stacked Auto-Encoders
4.3 Semi-Supervised and Partially Supervised Training
5. Variants of RBMs and Auto-Encoders
5.1 Sparse Representations in Auto-Encoder and RBMs
5.2 Denoising Auto-Encoders
5.3 Lateral Connections
5.4 Conditional RBMs and Temporal RBMs
5.5 Factored RBMs
5.6 Generalizing RBMs and Contrastive Divergence
6. Stochastic Variational Bounds for Joint Optimization of DBN Layers
6.1 Unfolding RBMs into Infinite Directed Belief Networks
6.2 Variational Justification of Greedy Layer-wise Training
6.3 Joint Unsupervised Training of All the Layers
7. Looking Forward
7.1 Global Optimization Strategies
7.2 Why Unsupervised Learning is Important
7.3 Open Questions
- No. of pages: 200
- Language: English
- Edition: 1
- Published: December 1, 2029
- Imprint: Academic Press
- eBook ISBN: 9780323906715
DR
Danda B. Rawat
Danda B. Rawat is a Full Professor in the Department of Electrical Engineering & Computer Science (EECS), Founding Director of the Howard University Data Science and Cybersecurity Center (DSC2), Founding Director of Cyber-security and Wireless Networking Innovations (CWiNs) Research Lab, Graduate Program Director of Howard-CS Graduate Programs and Director of Graduate Cybersecurity Certificate Program at Howard University, Washington, DC, USA. Dr. Rawat is engaged in research and teaching in the areas of cybersecurity, machine learning and wireless networking for emerging networked systems including cyber-physical systems, Internet-of-Things, smart cities, software defined systems and vehicular networks. His professional career comprises more than 15 years in academia, government, and industry. He has secured over $4 million in research funding from US National Science Foundation, US Department of Homeland Security, Department of Energy, National Nuclear Security Administration (NNSA), DoD Research Labs, Industry (Microsoft, Intel, etc.) and private Foundations. Dr. Rawat is the recipient of NSF CAREER Award in 2016, the US Air Force Research Laboratory (AFRL) Summer Faculty Visiting Fellowship in 2017, Outstanding Research Faculty Award (Award for Excellence in Scholarly Activity) at GSU in 2015, the Best Paper Awards and Outstanding PhD Researcher Award in 2009. He has delivered over 15 Keynotes and invited speeches at international conferences and workshops. Dr. Rawat has published over 200 scientific/technical articles and 9 books. He has been serving as an Editor/Guest Editor for over 30 international journals. He has been in Organizing Committees for several IEEE flagship conferences such as IEEE INFOCOM, IEEE CNS, IEEE ICC, IEEE CCNC and so on. Dr. Rawat received the Ph.D. degree from Old Dominion University, Norfolk, Virginia. Dr. Rawat is a Senior Member of IEEE and ACM, a member of ASEE. and a Fellow of the Institution of Engineering and Technology (IET). ..
Affiliations and expertise
Assistant Professor, Department of Electrical Engineering & Computer Science (EECS), Howard University, Washington, DC, USAM
Aaisha Makkar
Aaisha Makkar received her Ph.D. degree from the Computer Science and Engineering Department in Thapar Institute of Engineering & Technology, Patiala(Punjab), India. Her research interests in data mining, web mining, algorithms, machine learning, deep learning and Internet of things. She has experience of more than 10 years in teaching and research. She is the author of a machine learning book, entitled ”Machine Learning in Cognitive IoT”. Dr. Makkar has secured a number of research articles in top-tier journals as well as international conferences. Some of these are IEEE Transactions on Industrial Informatics, Future Generation Computer Systems , IEEE IoT Journal, Information Sciences, IEEE Globecom. She has organized various special sessions at esteemed international conferences. She is a member of IEEE, IEEE CIS, and ACM.
Affiliations and expertise
Research Scholar, Computer Science and Engineering Department, Thapar Institute of Engineering & Technology, Patiala(Punjab), IndiaPC
Pushpita Chatterjee
Pushpita Chatterjee is a Research Consultant at Old Dominion University, VA since 2016. Pushpita received her PhD from Indian Institute of Technology Kharagpur, India in 2012 under supervision of Prof. Indranil Sengupta ad Prof. Soumya K Ghosh. She received her MTech in Computer Engineering and MS in Computer and Information Science from University of Calcutta 2004, and 2002 respectively. Prior to joining ODU, she was a Senior Research Lead in SRM Institute of Science and Technology, (a Unit of SRM University, Chennai), Bangalore, India. She was responsible for leading a group of 20+ researchers who were working for OpenFlow and Software defined Networking and Deep Learning related application research with NEC, Japan, and NTT, Japan. She has a good number of publications to her credit in international journals, conferences and books. Her research interests include smart health, machine learning, distributed and trust computing, wireless sensor networks, information-centric networking and software-defined networking. She is a member of IEEE.
Affiliations and expertise
Research Consultant, Old Dominion University, VA, USAUG
Uttam Ghosh
Uttam Ghosh is working as an Assistant Professor of the Practice in the Department of Electrical Engineering and Computer Science, Vanderbilt University, USA. Dr. Ghosh obtained his PhD in Electronics and Electrical Engineering from the Indian Institute of Technology Kharagpur, India in 2013, and has Post-doctoral experience at the University of Illinois in Urbana-Champaign, Fordham University, and Tennessee State University. Dr. Ghosh has conducted several sessions and workshops related to CPS, SDN, IoT and smart cities as co-chair at top international conferences including IEEE Globecom, Healthcom, MASS, SECON etc.. Dr. Ghosh is contributing as guest editor for special issues with IEEE, ACM, Springer, Elsevier, Wiley, and MDPI. He is a Senior Member of the IEEE and a member of AAAS, ASEE, ACM, and Sigma Xi. He is co-editing 10 books with Springer, CRC press. His main research interests include Cybersecurity, Computer Networks, Wireless Networks, Information Centric Networking and Software-Defined Networking.
Affiliations and expertise
Assistant Professor, Practice in the Department of Electrical Engineering and Computer Science, Vanderbilt University, USA