{"product_id":"cybersecurity-in-intelligent-networking-systems-isbn-9781119783916","title":"Cybersecurity in Intelligent Networking Systems","description":"\u003cb\u003eCYBERSECURITY IN INTELLIGENT NETWORKING SYSTEMS\u003c\/b\u003e \u003cp\u003e\u003cb\u003eHelp protect your network system with this important reference work on cybersecurity \u003c\/b\u003e \u003c\/p\u003e\u003cp\u003eCybersecurity and privacy are critical to modern network systems. As various malicious threats have been launched that target critical online services—such as e-commerce, e-health, social networks, and other major cyber applications—it has become more critical to protect important information from being accessed. Data-driven network intelligence is a crucial development in protecting the security of modern network systems and ensuring information privacy. \u003c\/p\u003e\u003cp\u003e\u003ci\u003eCybersecurity in Intelligent Networking Systems\u003c\/i\u003e provides a background introduction to data-driven cybersecurity, privacy preservation, and adversarial machine learning. It offers a comprehensive introduction to exploring technologies, applications, and issues in data-driven cyber infrastructure. It describes a proposed novel, data-driven network intelligence system that helps provide robust and trustworthy safeguards with edge-enabled cyber infrastructure, edge-enabled artificial intelligence (AI) engines, and threat intelligence. Focusing on encryption-based security protocol, this book also highlights the capability of a network intelligence system in helping target and identify unauthorized access, malicious interactions, and the destruction of critical information and communication technology. \u003c\/p\u003e\u003cp\u003e\u003ci\u003eCybersecurity in Intelligent Networking Systems \u003c\/i\u003ereaders will also find: \u003c\/p\u003e\u003cul\u003e\n\u003cli\u003e Fundamentals in AI for cybersecurity, including artificial intelligence, machine learning, and security threats\u003c\/li\u003e \u003cli\u003e Latest technologies in data-driven privacy preservation, including differential privacy, federated learning, and homomorphic encryption\u003c\/li\u003e \u003cli\u003e Key areas in adversarial machine learning, from both offense and defense perspectives\u003c\/li\u003e \u003cli\u003e Descriptions of network anomalies and cyber threats\u003c\/li\u003e \u003cli\u003e Background information on data-driven network intelligence for cybersecurity\u003c\/li\u003e \u003cli\u003e Robust and secure edge intelligence for network anomaly detection against cyber intrusions\u003c\/li\u003e \u003cli\u003e Detailed descriptions of the design of privacy-preserving security protocols\u003c\/li\u003e\n\u003c\/ul\u003e \u003cp\u003e\u003ci\u003eCybersecurity in Intelligent Networking Systems \u003c\/i\u003eis an essential reference for all professional computer engineers and researchers in cybersecurity and artificial intelligence, as well as graduate students in these fields. \u003c\/p\u003e\u003cp\u003eContents\u003c\/p\u003e \u003cp\u003ePreface xiii\u003c\/p\u003e \u003cp\u003eAcknowledgments xvii\u003c\/p\u003e \u003cp\u003eAcronyms xix\u003c\/p\u003e \u003cp\u003e1 Cybersecurity in the Era of Artificial Intelligence 1\u003c\/p\u003e \u003cp\u003e1.1 Artificial Intelligence for Cybersecurity . 2\u003c\/p\u003e \u003cp\u003e1.1.1 Artificial Intelligence 2\u003c\/p\u003e \u003cp\u003e1.1.2 Machine Learning 4\u003c\/p\u003e \u003cp\u003e1.1.3 Data-Driven Workflow for Cybersecurity . 6\u003c\/p\u003e \u003cp\u003e1.2 Key Areas and Challenges 7\u003c\/p\u003e \u003cp\u003e1.2.1 Anomaly Detection . 8\u003c\/p\u003e \u003cp\u003e1.2.2 Trustworthy Artificial Intelligence . 10\u003c\/p\u003e \u003cp\u003e1.2.3 Privacy Preservation . 10\u003c\/p\u003e \u003cp\u003e1.3 Toolbox to Build Secure and Intelligent Systems . 11\u003c\/p\u003e \u003cp\u003e1.3.1 Machine Learning and Deep Learning . 12\u003c\/p\u003e \u003cp\u003e1.3.2 Privacy-Preserving Machine Learning . 14\u003c\/p\u003e \u003cp\u003e1.3.3 Adversarial Machine Learning . 15\u003c\/p\u003e \u003cp\u003e1.4 Data Repositories for Cybersecurity Research . 16\u003c\/p\u003e \u003cp\u003e1.4.1 NSL-KDD . 17\u003c\/p\u003e \u003cp\u003e1.4.2 UNSW-NB15 . 17\u003c\/p\u003e \u003cp\u003ev\u003c\/p\u003e \u003cp\u003e1.4.3 EMBER 18\u003c\/p\u003e \u003cp\u003e1.5 Summary 18\u003c\/p\u003e \u003cp\u003e2 Cyber Threats and Gateway Defense 19\u003c\/p\u003e \u003cp\u003e2.1 Cyber Threats . 19\u003c\/p\u003e \u003cp\u003e2.1.1 Cyber Intrusions . 20\u003c\/p\u003e \u003cp\u003e2.1.2 Distributed Denial of Services Attack . 22\u003c\/p\u003e \u003cp\u003e2.1.3 Malware and Shellcode . 23\u003c\/p\u003e \u003cp\u003e2.2 Gateway Defense Approaches 23\u003c\/p\u003e \u003cp\u003e2.2.1 Network Access Control 24\u003c\/p\u003e \u003cp\u003e2.2.2 Anomaly Isolation 24\u003c\/p\u003e \u003cp\u003e2.2.3 Collaborative Learning . 24\u003c\/p\u003e \u003cp\u003e2.2.4 Secure Local Data Learning 25\u003c\/p\u003e \u003cp\u003e2.3 Emerging Data-Driven Methods for Gateway Defense 26\u003c\/p\u003e \u003cp\u003e2.3.1 Semi-Supervised Learning for Intrusion Detection 26\u003c\/p\u003e \u003cp\u003e2.3.2 Transfer Learning for Intrusion Detection 27\u003c\/p\u003e \u003cp\u003e2.3.3 Federated Learning for Privacy Preservation . 28\u003c\/p\u003e \u003cp\u003e2.3.4 Reinforcement Learning for Penetration Test 29\u003c\/p\u003e \u003cp\u003e2.4 Case Study: Reinforcement Learning for Automated Post-Breach\u003c\/p\u003e \u003cp\u003ePenetration Test . 30\u003c\/p\u003e \u003cp\u003e2.4.1 Literature Review 30\u003c\/p\u003e \u003cp\u003e2.4.2 Research Idea 31\u003c\/p\u003e \u003cp\u003e2.4.3 Training Agent using Deep Q-Learning 32\u003c\/p\u003e \u003cp\u003e2.5 Summary 34\u003c\/p\u003e \u003cp\u003evi\u003c\/p\u003e \u003cp\u003e3 Edge Computing and Secure Edge Intelligence 35\u003c\/p\u003e \u003cp\u003e3.1 Edge Computing . 35\u003c\/p\u003e \u003cp\u003e3.2 Key Advances in Edge Computing . 38\u003c\/p\u003e \u003cp\u003e3.2.1 Security 38\u003c\/p\u003e \u003cp\u003e3.2.2 Reliability . 41\u003c\/p\u003e \u003cp\u003e3.2.3 Survivability . 42\u003c\/p\u003e \u003cp\u003e3.3 Secure Edge Intelligence . 43\u003c\/p\u003e \u003cp\u003e3.3.1 Background and Motivation 44\u003c\/p\u003e \u003cp\u003e3.3.2 Design of Detection Module 45\u003c\/p\u003e \u003cp\u003e3.3.3 Challenges against Poisoning Attacks . 48\u003c\/p\u003e \u003cp\u003e3.4 Summary 49\u003c\/p\u003e \u003cp\u003e4 Edge Intelligence for Intrusion Detection 51\u003c\/p\u003e \u003cp\u003e4.1 Edge Cyberinfrastructure . 51\u003c\/p\u003e \u003cp\u003e4.2 Edge AI Engine 53\u003c\/p\u003e \u003cp\u003e4.2.1 Feature Engineering . 53\u003c\/p\u003e \u003cp\u003e4.2.2 Model Learning . 54\u003c\/p\u003e \u003cp\u003e4.2.3 Model Update 56\u003c\/p\u003e \u003cp\u003e4.2.4 Predictive Analytics . 56\u003c\/p\u003e \u003cp\u003e4.3 Threat Intelligence 57\u003c\/p\u003e \u003cp\u003e4.4 Preliminary Study . 57\u003c\/p\u003e \u003cp\u003e4.4.1 Dataset 57\u003c\/p\u003e \u003cp\u003e4.4.2 Environment Setup . 59\u003c\/p\u003e \u003cp\u003e4.4.3 Performance Evaluation . 59\u003c\/p\u003e \u003cp\u003evii\u003c\/p\u003e \u003cp\u003e4.5 Summary 63\u003c\/p\u003e \u003cp\u003e5 Robust Intrusion Detection 65\u003c\/p\u003e \u003cp\u003e5.1 Preliminaries 65\u003c\/p\u003e \u003cp\u003e5.1.1 Median Absolute Deviation . 65\u003c\/p\u003e \u003cp\u003e5.1.2 Mahalanobis Distance 66\u003c\/p\u003e \u003cp\u003e5.2 Robust Intrusion Detection . 67\u003c\/p\u003e \u003cp\u003e5.2.1 Problem Formulation 67\u003c\/p\u003e \u003cp\u003e5.2.2 Step 1: Robust Data Preprocessing 68\u003c\/p\u003e \u003cp\u003e5.2.3 Step 2: Bagging for Labeled Anomalies 69\u003c\/p\u003e \u003cp\u003e5.2.4 Step 3: One-Class SVM for Unlabeled Samples . 70\u003c\/p\u003e \u003cp\u003e5.2.5 Step 4: Final Classifier . 74\u003c\/p\u003e \u003cp\u003e5.3 Experiment and Evaluation . 76\u003c\/p\u003e \u003cp\u003e5.3.1 Experiment Setup 76\u003c\/p\u003e \u003cp\u003e5.3.2 Performance Evaluation . 81\u003c\/p\u003e \u003cp\u003e5.4 Summary 92\u003c\/p\u003e \u003cp\u003e6 Efficient Preprocessing Scheme for Anomaly Detection 93\u003c\/p\u003e \u003cp\u003e6.1 Efficient Anomaly Detection . 93\u003c\/p\u003e \u003cp\u003e6.1.1 Related Work . 95\u003c\/p\u003e \u003cp\u003e6.1.2 Principal Component Analysis . 97\u003c\/p\u003e \u003cp\u003e6.2 Efficient Preprocessing Scheme for Anomaly Detection . 98\u003c\/p\u003e \u003cp\u003e6.2.1 Robust Preprocessing Scheme . 99\u003c\/p\u003e \u003cp\u003e6.2.2 Real-Time Processing 103\u003c\/p\u003e \u003cp\u003eviii\u003c\/p\u003e \u003cp\u003e6.2.3 Discussions 103\u003c\/p\u003e \u003cp\u003e6.3 Case Study . 104\u003c\/p\u003e \u003cp\u003e6.3.1 Description of the Raw Data 105\u003c\/p\u003e \u003cp\u003e6.3.2 Experiment 106\u003c\/p\u003e \u003cp\u003e6.3.3 Results 108\u003c\/p\u003e \u003cp\u003e6.4 Summary 109\u003c\/p\u003e \u003cp\u003e7 Privacy Preservation in the Era of Big Data 111\u003c\/p\u003e \u003cp\u003e7.1 Privacy Preservation Approaches 111\u003c\/p\u003e \u003cp\u003e7.1.1 Anonymization 111\u003c\/p\u003e \u003cp\u003e7.1.2 Differential Privacy . 112\u003c\/p\u003e \u003cp\u003e7.1.3 Federated Learning . 114\u003c\/p\u003e \u003cp\u003e7.1.4 Homomorphic Encryption 116\u003c\/p\u003e \u003cp\u003e7.1.5 Secure Multi-Party Computation . 117\u003c\/p\u003e \u003cp\u003e7.1.6 Discussions 118\u003c\/p\u003e \u003cp\u003e7.2 Privacy-Preserving Anomaly Detection . 120\u003c\/p\u003e \u003cp\u003e7.2.1 Literature Review 121\u003c\/p\u003e \u003cp\u003e7.2.2 Preliminaries . 123\u003c\/p\u003e \u003cp\u003e7.2.3 System Model and Security Model 124\u003c\/p\u003e \u003cp\u003e7.3 Objectives and Workflow . 126\u003c\/p\u003e \u003cp\u003e7.3.1 Objectives . 126\u003c\/p\u003e \u003cp\u003e7.3.2 Workflow . 128\u003c\/p\u003e \u003cp\u003e7.4 Predicate Encryption based Anomaly Detection . 129\u003c\/p\u003e \u003cp\u003e7.4.1 Procedures 129\u003c\/p\u003e \u003cp\u003eix\u003c\/p\u003e \u003cp\u003e7.4.2 Development of Predicate . 131\u003c\/p\u003e \u003cp\u003e7.4.3 Deployment of Anomaly Detection 132\u003c\/p\u003e \u003cp\u003e7.5 Case Study and Evaluation . 134\u003c\/p\u003e \u003cp\u003e7.5.1 Overhead . 134\u003c\/p\u003e \u003cp\u003e7.5.2 Detection . 136\u003c\/p\u003e \u003cp\u003e7.6 Summary 137\u003c\/p\u003e \u003cp\u003e8 Adversarial Examples: Challenges and Solutions 139\u003c\/p\u003e \u003cp\u003e8.1 Adversarial Examples . 139\u003c\/p\u003e \u003cp\u003e8.1.1 Problem Formulation in Machine Learning 140\u003c\/p\u003e \u003cp\u003e8.1.2 Creation of Adversarial Examples . 141\u003c\/p\u003e \u003cp\u003e8.1.3 Targeted and Non-Targeted Attacks . 141\u003c\/p\u003e \u003cp\u003e8.1.4 Black-Box and White-Box Attacks 142\u003c\/p\u003e \u003cp\u003e8.1.5 Defenses against Adversarial Examples 142\u003c\/p\u003e \u003cp\u003e8.2 Adversarial Attacks in Security Applications 143\u003c\/p\u003e \u003cp\u003e8.2.1 Malware 143\u003c\/p\u003e \u003cp\u003e8.2.2 Cyber Intrusions . 143\u003c\/p\u003e \u003cp\u003e8.3 Case Study: Improving Adversarial Attacks Against Malware\u003c\/p\u003e \u003cp\u003eDetectors 144\u003c\/p\u003e \u003cp\u003e8.3.1 Background 144\u003c\/p\u003e \u003cp\u003e8.3.2 Adversarial Attacks on Malware Detectors 145\u003c\/p\u003e \u003cp\u003e8.3.3 MalConv Architecture 147\u003c\/p\u003e \u003cp\u003e8.3.4 Research Idea 148\u003c\/p\u003e \u003cp\u003e8.4 Case Study: A Metric for Machine Learning Vulnerability to\u003c\/p\u003e \u003cp\u003eAdversarial Examples . 149\u003c\/p\u003e \u003cp\u003e8.4.1 Background 149\u003c\/p\u003e \u003cp\u003e8.4.2 Research Idea 150\u003c\/p\u003e \u003cp\u003e8.5 Case Study: Protecting Smart Speakers from Adversarial Voice\u003c\/p\u003e \u003cp\u003eCommands . 153\u003c\/p\u003e \u003cp\u003e8.5.1 Background 153\u003c\/p\u003e \u003cp\u003e8.5.2 Challenges 154\u003c\/p\u003e \u003cp\u003e8.5.3 Directions and Tasks 155\u003c\/p\u003e \u003cp\u003e8.6 Summary 157\u003c\/p\u003e \u003cp\u003exi\u003c\/p\u003e  \u003cp\u003e\u003cb\u003eShengjie Xu, PhD, \u003c\/b\u003eis an IEEE member and is an Assistant Professor in the Management Information Systems Department at San Diego State University, USA. \u003c\/p\u003e\u003cp\u003e\u003cb\u003eYi Qian, PhD, \u003c\/b\u003eis an IEEE Fellow and is a Professor in the Department of Electrical and Computer Engineering at the University of Nebraska-Lincoln, USA. \u003c\/p\u003e\u003cp\u003e\u003cb\u003eRose Qingyang Hu, PhD, \u003c\/b\u003eis an IEEE Fellow. She is also a Professor with the Electrical and Computer Engineering Department and the Associate Dean for Research of the College of Engineering, Utah State University, USA.   \u003c\/p\u003e\u003cp\u003e\u003cb\u003eHelp protect your network system with this important reference work on cybersecurity \u003c\/b\u003e \u003c\/p\u003e\u003cp\u003eCybersecurity and privacy are critical to modern network systems. As various malicious threats have been launched that target critical online services—such as e-commerce, e-health, social networks, and other major cyber applications—it has become more critical to protect important information from being accessed. Data-driven network intelligence is a crucial development in protecting the security of modern network systems and ensuring information privacy. \u003c\/p\u003e\u003cp\u003e\u003ci\u003eCybersecurity in Intelligent Networking Systems\u003c\/i\u003e provides a background introduction to data-driven cybersecurity, privacy preservation, and adversarial machine learning. It offers a comprehensive introduction to exploring technologies, applications, and issues in data-driven cyber infrastructure. It describes a proposed novel, data-driven network intelligence system that helps provide robust and trustworthy safeguards with edge-enabled cyber infrastructure, edge-enabled artificial intelligence (AI) engines, and threat intelligence. Focusing on encryption-based security protocol, this book also highlights the capability of a network intelligence system in helping target and identify unauthorized access, malicious interactions, and the destruction of critical information and communication technology. \u003c\/p\u003e\u003cp\u003e\u003ci\u003eCybersecurity in Intelligent Networking Systems \u003c\/i\u003ereaders will also find: \u003c\/p\u003e\u003cul\u003e\n\u003cli\u003e Fundamentals in AI for cybersecurity, including artificial intelligence, machine learning, and security threats\u003c\/li\u003e \u003cli\u003e Latest technologies in data-driven privacy preservation, including differential privacy, federated learning, and homomorphic encryption\u003c\/li\u003e \u003cli\u003e Key areas in adversarial machine learning, from both offense and defense perspectives\u003c\/li\u003e \u003cli\u003e Descriptions of network anomalies and cyber threats\u003c\/li\u003e \u003cli\u003e Background information on data-driven network intelligence for cybersecurity\u003c\/li\u003e \u003cli\u003e Robust and secure edge intelligence for network anomaly detection against cyber intrusions\u003c\/li\u003e \u003cli\u003e Detailed descriptions of the design of privacy-preserving security protocols\u003c\/li\u003e\n\u003c\/ul\u003e \u003cp\u003e\u003ci\u003eCybersecurity in Intelligent Networking Systems \u003c\/i\u003eis\u003ci\u003e \u003c\/i\u003ean essential reference for all professional computer engineers and researchers in cybersecurity and artificial intelligence, as well as graduate students in these fields.\u003c\/p\u003e","brand":"Wiley-IEEE Press","offers":[{"title":"Default Title","offer_id":47989019574501,"sku":"NP9781119783916","price":135.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1842\/7735\/files\/9781119783916.jpg?v=1761782464","url":"https:\/\/k12savings.com\/products\/cybersecurity-in-intelligent-networking-systems-isbn-9781119783916","provider":"K12savings","version":"1.0","type":"link"}