Deep Learning Approaches to Cloud Security

Pramod Singh Rathore, PhD, is an assistant professor in the computer science and engineering department at the Aryabhatta Engineering College and Research Centre, Ajmer, Rajasthan, India and is also visiting faculty at the Government University, MDS Ajmer. He has over eight years of teaching experience and more than 45 publications in peer-reviewed journals, books, and conferences. He has also co-authored and edited numerous books with a variety of global publishers, such as the imprint, Wiley-Scrivener.Vishal Dutt, PhD, received his doctorate in computer science from the University of Madras, and he is an assistant professor in the computer science and engineering department at the Aryabhatta Engineering College in Ajmer, as well as visiting faculty at Maharshi Dayanand Saraswati University in Ajmer. He has four years of teaching experience and has more than 22 publications in peer-reviewed scientific and technical journals. He has also been working as a freelance writer for more than six years in the fields of data analytics, Java, Assembly Programmer, Desktop Designer, and Android Developer. Rashmi Agrawal, PhD, is a professor in the Department of Computer Applications at Manav Rachna International Institute of Research and Studies in Faridabad, India. She has over 18 years of experience in teaching and research and is a book series editor for a series on big data and machine learning. She has authored or coauthored numerous research papers in peer-reviewed scientific and technical journals and conferences and has also edited or authored books with a number of large book publishers, in imprints such as Wiley-Scrivener. She is also an active reviewer and editorial board member in various journals. Satya Murthy Sasubilli is a solutions architect with the Huntington National Bank, having received his masters in computer applications from the University of Madras, India. He has more than 15 years of experience in cloud-based technologies like big data solutions, cloud infrastructure, digital analytics delivery, data warehousing, and many others. He has worked with many Fortune 500 organizations, such as Infosys, Capgemini, and others and is an active reviewer for several scientific and technical journals. Srinivasa Rao Swarna is a program manager and senior data architect at Tata Consultancy Services in the USA. He received his BTech in chemical engineering from Jawaharlal Nehru Technological University, Hyderabad, India and completed his internship at Volkswagen AG, Wolfsburg, Germany in 2004. He has over 16 years of experience in this area, having worked with many Fortune 500 companies, and he is a frequent reviewer for several scientific and technical journals.

• Foreword xvPreface xvii1 Biometric Identification Using Deep Learning for Advance Cloud Security 1Navani Siroya and Manju Mandot1.1 Introduction 21.2 Techniques of Biometric Identification 31.2.1 Fingerprint Identification 31.2.2 Iris Recognition 41.2.3 Facial Recognition 41.2.4 Voice Recognition 51.3 Approaches 61.3.1 Feature Selection 61.3.2 Feature Extraction 61.3.3 Face Marking 71.3.4 Nearest Neighbor Approach 81.4 Related Work, A Review 91.5 Proposed Work 101.6 Future Scope 121.7 Conclusion 12References 122 Privacy in Multi-Tenancy Cloud Using Deep Learning 15Shweta Solanki and Prafull Narooka2.1 Introduction 152.2 Basic Structure 162.2.1 Basic Structure of Cloud Computing 172.2.2 Concept of Multi-Tenancy 182.2.3 Concept of Multi-Tenancy with Cloud Computing 192.3 Privacy in Cloud Environment Using Deep Learning 212.4 Privacy in Multi-Tenancy with Deep Learning Concept 222.5 Related Work 232.6 Conclusion 24References 253 Emotional Classification Using EEG Signals and Facial Expression: A Survey 27S J Savitha, Dr. M Paulraj and K Saranya3.1 Introduction 273.2 Related Works 293.3 Methods 323.3.1 EEG Signal Pre-Processing 323.3.1.1 Discrete Fourier Transform (DFT) 323.3.1.2 Least Mean Square (LMS) Algorithm 323.3.1.3 Discrete Cosine Transform (DCT) 333.3.2 Feature Extraction Techniques 333.3.3 Classification Techniques 333.4 BCI Applications 343.4.1 Possible BCI Uses 363.4.2 Communication 363.4.3 Movement Control 363.4.4 Environment Control 373.4.5 Locomotion 383.5 Cloud-Based EEG Overview 383.5.1 Data Backup and Restoration 393.6 Conclusion 40References 404 Effective and Efficient Wind Power Generation Using Bifarious Solar PV System 43R. Amirtha Katesa Sai Raj, M. Arun Kumar, S. Dinesh, U. Harisudhan and Dr. R. Uthirasamy4.1 Introduction 444.2 Study of Bi-Facial Solar Panel 454.3 Proposed System 464.3.1 Block Diagram 464.3.2 DC Motor Mechanism 474.3.3 Battery Bank 484.3.4 System Management Using IoT 484.3.5 Structure of Proposed System 504.3.6 Spoiler Design 514.3.7 Working Principle of Proposed System 524.3.8 Design and Analysis 534.4 Applications of IoT in Renewable Energy Resources 534.4.1 Wind Turbine Reliability Using IoT 544.4.2 Siting of Wind Resource Using IoT 554.4.3 Application of Renewable Energy in Medical Industries 564.4.4 Data Analysis Using Deep Learning 574.5 Conclusion 59References 595 Background Mosaicing Model for Wide Area Surveillance System 63Dr. E. Komagal5.1 Introduction 645.2 Related Work 645.3 Methodology 655.3.1 Feature Extraction 665.3.2 Background Deep Learning Model Based on Mosaic 675.3.3 Foreground Segmentation 705.4 Results and Discussion 705.5 Conclusion 72References 726 Prediction of CKD Stage 1 Using Three Different Classifiers 75Thamizharasan, K., Yamini, P., Shimola, A. and Sudha, S.6.1 Introduction 756.2 Materials and Methods 786.3 Results and Discussion 846.4 Conclusions and Future Scope 89References 897 Classification of MRI Images to Aid in Diagnosis of Neurological Disorder Using SVM 93Phavithra Selvaraj, Sruthi, M.S., Sridaran, M. and Dr. Jobin Christ M.C.7.1 Introduction 937.2 Methodology 957.2.1 Data Acquisition 957.2.2 Image Preprocessing 967.2.3 Segmentation 977.2.4 Feature Extraction 987.2.5 Classification 997.3 Results and Discussions 1007.3.1 Preprocessing 1007.3.2 Classification 1037.3.3 Validation 1047.4 Conclusion 106References 1068 Convolutional Networks 109Simran Kaur and Rashmi Agrawal8.1 Introduction 1108.2 Convolution Operation 1108.3 CNN 1108.4 Practical Applications 1128.4.1 Audio Data 1128.4.2 Image Data 1128.4.3 Text Data 1138.5 Challenges of Profound Models 1138.6 Deep Learning In Object Detection 1148.7 CNN Architectures 1148.8 Challenges of Item Location 1188.8.1 Scale Variation Problem 1188.8.2 Occlusion Problem 1198.8.3 Deformation Problem 120References 1219 Categorization of Cloud Computing & Deep Learning 123Disha Shrmali9.1 Introduction to Cloud Computing 1239.1.1 Cloud Computing 1239.1.2 Cloud Computing: History and Evolution 1249.1.3 Working of Cloud 1259.1.4 Characteristics of Cloud Computing 1279.1.5 Different Types of Cloud Computing Service Models 1289.1.5.1 Infrastructure as A Service (IAAS) 1289.1.5.2 Platform as a Service (PAAS) 1299.1.5.3 Software as a Service (SAAS) 1299.1.6 Cloud Computing Advantages and Disadvantages 1309.1.6.1 Advantages of Cloud Computing 1309.1.6.2 Disadvantages of Cloud Computing 1329.2 Introduction to Deep Learning 1339.2.1 History and Revolution of Deep Learning 1349.2.1.1 Development of Deep Learning Algorithms 1349.2.1.2 The FORTRAN Code for Back Propagation 1359.2.1.3 Deep Learning from the 2000s and Beyond 1359.2.1.4 The Cat Experiment 1369.2.2 Neural Networks 1379.2.2.1 Artificial Neural Networks 1379.2.2.2 Deep Neural Networks 1389.2.3 Applications of Deep Learning 1389.2.3.1 Automatic Speech Recognition 1389.2.3.2 Electromyography (EMG) Recognition 1399.2.3.3 Image Recognition 1399.2.3.4 Visual Art Processing 1409.2.3.5 Natural Language Processing 1409.2.3.6 Drug Discovery and Toxicology 1409.2.3.7 Customer Relationship Management 1419.2.3.8 Recommendation Systems 1419.2.3.9 Bioinformatics 1419.2.3.10 Medical Image Analysis 1419.2.3.11 Mobile Advertising 1419.2.3.12 Image Restoration 1429.2.3.13 Financial Fraud Detection 1429.2.3.14 Military 1429.3 Conclusion 142References 14310 Smart Load Balancing in Cloud Using Deep Learning 145Astha Parihar and Shweta Sharma10.1 Introduction 14610.2 Load Balancing 14710.2.1 Static Algorithm 14810.2.2 Dynamic (Run-Time) Algorithms 14810.3 Load Adjusting in Distributing Computing 14910.3.1 Working of Load Balancing 15110.4 Cloud Load Balancing Criteria (Measures) 15210.5 Load Balancing Proposed for Cloud Computing 15310.5.1 Calculation of Load Balancing in the Whole System 15410.6 Load Balancing in Next Generation Cloud Computing 15510.7 Dispersed AI Load Adjusting Methodology in Distributed Computing Administrations 15710.7.1 Quantum Isochronous Parallel 15810.7.2 Phase Isochronous Parallel 15910.7.3 Dynamic Isochronous Coordinate Strategy 16110.8 Adaptive-Dynamic Synchronous Coordinate Strategy 16110.8.1 Adaptive Quick Reassignment (AdaptQR) 16210.8.2 A-DIC (Adaptive-Dynamic Synchronous Parallel) 16310.9 Conclusion 164References 16511 Biometric Identification for Advanced Cloud Security 167Yojna khandelwal and Kapil Chauhan11.1 Introduction 16811.1.1 Biometric Identification 16811.1.2 Biometric Characteristic 16911.1.3 Types of Biometric Data 16911.1.3.1 Face Recognition 16911.1.3.2 Hand Vein 17011.1.3.3 Signature Verification 17011.1.3.4 Iris Recognition 17011.1.3.5 Voice Recognition 17011.1.3.6 Fingerprints 17111.2 Literature Survey 17211.3 Biometric Identification in Cloud Computing 17411.3.1 How Biometric Authentication is Being Used on the Cloud Platform 17611.4 Models and Design Goals 17711.4.1 Models 17711.4.1.1 System Model 17711.4.1.2 Threat Model 17711.4.2 Design Goals 17811.5 Face Recognition Method as a Biometric Authentication 17911.6 Deep Learning Techniques for Big Data in Biometrics 18011.6.1 Issues and Challenges 18111.6.2 Deep Learning Strategies For Biometric Identification 18211.7 Conclusion 185References 18512 Application of Deep Learning in Cloud Security 189Jaya Jain12.1 Introduction 19012.2 Literature Review 19112.3 Deep Learning 19212.4 The Uses of Fields in Deep Learning 19512.5 Conclusion 202References 20313 Real Time Cloud Based Intrusion Detection 207Ekta Bafna13.1 Introduction 20713.2 Literature Review 20913.3 Incursion In Cloud 21113.3.1 Denial of Service (DoS) Attack 21213.3.2 Insider Attack 21213.3.3 User To Root (U2R) Attack 21313.3.4 Port Scanning 21313.4 Intrusion Detection System 21313.4.1 Signature-Based Intrusion Detection System (SIDS) 21313.4.2 Anomaly-Based Intrusion Detection System (AIDS) 21413.4.3 Intrusion Detection System Using Deep Learning 21513.5 Types of IDS in Cloud 21613.5.1 Host Intrusion Detection System 21613.5.2 Network Based Intrusion Detection System 21713.5.3 Distributed Based Intrusion Detection System 21713.6 Model of Deep Learning 21813.6.1 ConvNet Model 21813.6.2 Recurrent Neural Network 21913.6.3 Multi-Layer Perception Model 21913.7 KDD Dataset 22113.8 Evaluation 22113.9 Conclusion 223References 22314 Applications of Deep Learning in Cloud Security 225Disha Shrmali and Shweta Sharma14.1 Introduction 22614.1.1 Data Breaches 22614.1.2 Accounts Hijacking 22714.1.3 Insider Threat 22714.1.3.1 Malware Injection 22714.1.3.2 Abuse of Cloud Services 22814.1.3.3 Insecure APIs 22814.1.3.4 Denial of Service Attacks 22814.1.3.5 Insufficient Due Diligence 22914.1.3.6 Shared Vulnerabilities 22914.1.3.7 Data Loss 22914.2 Deep Learning Methods for Cloud Cyber Security 23014.2.1 Deep Belief Networks 23014.2.1.1 Deep Autoencoders 23014.2.1.2 Restricted Boltzmann Machines 23214.2.1.3 DBNs, RBMs, or Deep Autoencoders Coupled with Classification Layers 23314.2.1.4 Recurrent Neural Networks 23314.2.1.5 Convolutional Neural Networks 23414.2.1.6 Generative Adversarial Networks 23514.2.1.7 Recursive Neural Networks 23614.2.2 Applications of Deep Learning in Cyber Security 23714.2.2.1 Intrusion Detection and Prevention Systems (IDS/IPS) 23714.2.2.2 Dealing with Malware 23714.2.2.3 Spam and Social Engineering Detection 23814.2.2.4 Network Traffic Analysis 23814.2.2.5 User Behaviour Analytics 23814.2.2.6 Insider Threat Detection 23914.2.2.7 Border Gateway Protocol Anomaly Detection 23914.2.2.8 Verification if Keystrokes were Typed by a Human 24014.3 Framework to Improve Security in Cloud Computing 24014.3.1 Introduction to Firewalls 24114.3.2 Importance of Firewalls 24214.3.2.1 Prevents the Passage of Unwanted Content 24214.3.2.2 Prevents Unauthorized Remote Access 24314.3.2.3 Restrict Indecent Content 24314.3.2.4 Guarantees Security Based on Protocol and IP Address 24414.3.2.5 Protects Seamless Operations in Enterprises 24414.3.2.6 Protects Conversations and Coordination Contents 24414.3.2.7 Restricts Online Videos and Games from Displaying Destructive Content 24514.3.3 Types of Firewalls 24514.3.3.1 Proxy-Based Firewalls 24514.3.3.2 Stateful Firewalls 24614.3.3.3 Next-Generation Firewalls (NGF) 24714.3.3.4 Web Application Firewalls (WAF) 24714.3.3.5 Working of WAF 24814.3.3.6 How Web Application Firewalls (WAF) Work 24814.3.3.7 Attacks that Web Application Firewalls Prevent 25014.3.3.8 Cloud WAF 25114.4 WAF Deployment 25114.4.1 Web Application Firewall (WAF) Security Models 25214.4.2 Firewall-as-a-Service (FWaaS) 25214.4.3 Basic Difference Between a Cloud Firewall and a Next-Generation Firewall (NGFW) 25314.4.4 Introduction and Effects of Firewall Network Parameters on Cloud Computing 25314.5 Conclusion 254References 254About the Editors 257Index 263