Mariya Ouaissa is an assistant professor at Cadi Ayyad University, Morocco. Her research focuses on IoT, wireless and cyber-physical security.Hemant Kumar Saini is an academic at Lincoln University College, Malaysia, and Bennett University, Greater Noida, India. His research spans IoT, wireless networks and AI.Pankaj Bhambri is a post-doctoral researcher at Lincoln University College, Malaysia, and an associate professor at GNDEC, Ludhiana, India. His research specializes in ML, bioinformatics and WSNs.Mariyam Ouaissa is an assistant professor at ENSA, Chouaib Doukkali University, Morocco. Her research focuses on IoT, wireless networks and security.

• Preface xviiMariya OUAISSA, Hemant Kumar SAINI, Pankaj BHAMBRI and Mariyam OUAISSAChapter 1. Systemic Risks in Contemporary AI Systems: Misinformation, Model Dependency and Supply-Chain Vulnerabilities 1Saba FATIMA, C. Kishor Kumar REDDY, P.R. ANISHA, Umaima Qader MOHIUDDIN and Jothi PARANTHAMAN1.1. Introduction 21.2. Literature survey 31.3. Data as a strategic asset in modern digital systems 51.4. Threat landscape: AI systems under siege 71.5. Data abuse in AI pipelines 111.6. Ethical dilemmas across the AI lifecycle 141.7. Third-party model risks 241.8. AI and digital twins under siege 271.9. Combating dark intelligence: cyber resilience framework 281.10. Results and discussion 321.11. Conclusion 321.12. References 33Chapter 2. Data Abuse, Ethics Dilemmas, Supply Chain Poisoning and Third-Party Model Risks in the Age of AI Misinformation 37Shailja TRIPATHI and Laxmi Pandit VISHWAKARMA2.1. Introduction 382.2. Nature of AI and AI misinformation 392.3. Ethical dilemma generated by AI misinformation 412.4. Strategies for reducing ethical dilemmas caused by AI misinformation 492.5. Conclusion 562.6. Limitations and future scope 572.7. References 57Chapter 3. The Data Poisoning Problem in Digital Twin Intelligence: Foundations, Risks and Probabilistic Defense Strategies 65M'kouka BTISSAM, Zahedi CHAYMAA, Mariya OUAISSA and Mariyam OUAISSA3.1. Introduction 653.2. Digital twin foundations 663.3. Data poisoning problem 683.4. Risks for digital twins 703.5. Probabilistic defense strategies 723.6. Conceptual framework for data poisoning detection in digital twins 743.7. Future directions and conclusion 773.8. References 78Chapter 4. Adversarial Exploitation Lifecycle (AEL): Unveiling Dark Intelligence and Synthetic Identity Manipulation in Cognitive Security Systems 81Bebesh TRIPATHY, Apoorwa SINGH, Parul SOOD and ANNUPRIYA4.1. Introduction 824.2. Literature review 844.3. Conceptual foundations of synthetic identity and dark intelligence 874.4. Anatomy of the adversarial exploitation lifecycle (AEL) 934.5. Emerging attack strategies on synthetic identity systems 984.6. Result and evaluation 984.7. Challenges and limitations 1024.8. Future outcomes 1024.9. Conclusion 1034.10. References 104Chapter 5. Detecting Dark Intelligence in Cyber-Physical Digital Twins Using Self-Learning AI and Cognitive Security Analytics 107Preeti CHUGH, Imene Elhachfi ESSOUSSI, BABITA, SHUBNEET and Anushka Raj YADAV5.1. Introduction and motivation 1085.2. CPDT and self-learning fundamentals 1115.3. Dark intelligence threat extraction 1145.4. Stealth attack detection in twins 1175.5. Sensor and log analysis in CPDTs 1205.6. Model poisoning classification 1225.7. Twin vulnerability assessment 1265.8. Advanced self-learning techniques 1285.9. Case studies and evaluations 1315.10. Challenges and ethical considerations 1335.11. Conclusion 1365.12. References 137Chapter 6. A Hybrid Transformer Automata Framework for Behavioral Anomaly Detection of FraudGPT and Dark LLM Threats 143Ankita PATIL, Mritunjay Kr. RANJAN, Pankaj PATIL, Nitin MALI, Rajashri RIKAME and Disha ARSUDE6.1. Introduction 1446.2. Related work 1476.3. Problem statement 1486.4. Methodology 1506.5. System architecture 1586.6. Result and discussion 1586.7. Conclusion 1636.8. Future work 1646.9. References 164Chapter 7. Trusted Twin Security Architecture (TTSA): Enabling Autonomous Risk Mitigation and Cognitive Trust in AI-Driven Digital Twin Systems 169Bebesh TRIPATHY, Sudhanshu SHARMA and Pritesh TRIPATHY7.1. Introduction 1707.2. Literature review 1727.3. Threat landscape in digital twin and autonomous systems 1767.4. Autonomous risk mitigation framework 1787.5. Fundamentals of trusted twin security architecture 1837.6. Result and evaluation 1877.7. Challenges and limitations 1907.8. Future outcomes 1907.9. Conclusion 1917.10. References 192Chapter 8. Hybrid Cognitive-Explainable AI Architecture for Proactive Cyber Defense in Multi-Layer Networks 195Vaibhav SONAJE, Pranjal SONJE, Disha ARSUDE, Rajashri RIKAME, Ankita PATIL and Mritunjay Kr. RANJAN8.1. Introduction 1958.2. Related study 1988.3. Problem statement 1998.4. Methodology 2028.5. System architecture 2108.6. Result and discussion 2108.7. Conclusion 2148.8. Future work 2148.9. References 215Chapter 9. Adaptive Cyber Resilience via Bio-Inspired Computing: An ACRF-Based Autonomous Immune-System Defense Model 219Disha ARSUDE, Mritunjay Kr. RANJAN, Ramdas GORE, Kalyani PURKAR, Ankita PATIL and Rajashri RIKAME9.1. Introduction 2209.2. Related study 2239.3. Problem statement 2259.4. Methodology 2259.5. System architecture 2379.6. Result and discussion 2389.7. Conclusion 2419.8. Future work 2429.9. References 242Chapter 10. Neuro-Cognitive ML Framework for Deepfake Detection and Spoofed Sensor Integrity in Cyber–Physical Systems 247Rajashri RIKAME, Mritunjay Kr. RANJAN, Monali JADHAV, Sarika KONDEKAR, Disha ARSUDE and Ankita PATIL10.1. Introduction 24810.2. Related study 25010.3. Problem statement 25210.4. Methodology 25210.5. System architecture 26510.6. Result and discussion 26510.7. Conclusion 26910.8. Future work 27010.9. References 270Chapter 11. Explainable ML-Based Detection of Network-Based Fuzzing Attacks 273Nadeen AHMAD, Farida EMAM, Mouza ALAMERI and Mohammed M. ALANI11.1. Introduction 27311.2. Related works 27511.3. Proposed system 28011.4. Methodology 28111.5. Results and analysis 28511.6. Discussion. 29311.7. Conclusion 29511.8. References 296Chapter 12. A Unified Framework for Decentralized and Private Verification of Wearable Health Data using Blockchain and Zero Knowledge Proofs (ZKPs) 299Anant UPADHIYAY and Abhishek JAIN12.1. Introduction 30012.2. Related work 30012.3. Life cycle of privacy-preserving verification 30312.4. System design and architecture 30512.5. Implementation details 31012.6. Cloud native integration and operational view 31512.7. Result and discussion 31812.8. Conclusion 32312.9. Future work 32412.10. References 324Chapter 13. Identity-Centric Database Security for Resilient Cloud-Based Digital Twin Infrastructure 327Aktham AL-YAHYA and Qasem Abu AL-HAIJA13.1. Introduction 32713.2. Cloud authentication mechanisms 33013.3. Access control and identity management 33413.4. Database security in cloud environments 33813.5. Malware and insider threats in cloud databases 34113.6. Case study: the Capital One data breach 34313.7. Data-driven cloud security analytics 34613.8. Conclusions and future directions 34813.9. References 349Chapter 14. Protecting Smart Grid Digital Twins from Dark Intelligence Using Firewalls and Intrusion Detection Systems 353Akram AL-DHAFARI and Qasem Abu AL-HAIJA14.1. Introduction 35314.2. Smart grid architecture and threat landscape 35614.3. Firewall technologies for smart grids 35914.4. IDS/IPS 36314.5. Cryptography and authentication in smart grids 36614.6. Case study: the Ukraine power grid attack 36814.7. Data-driven threat analytics for smart grids 37014.8. Conclusions and future directions 37214.9. References 373Chapter 15. Big Data Analytics and AI-Driven Decision Support Systems for Financial Inclusion and Microfinance Risk Assessment 375Tanvir Mahmoud HUSSEIN, Kannadasan KARUPPAIAH, Palanivel R.M., Prabu NEETHIDOSS, Wajid Ahmed ANSARI, Abdul Saleem MOHAMMED, Abdul Waheed MOHAMMED, Sivasankar PRABAHARAN and Vinoth RAMAN15.1. Introduction 37515.2. Theoretical foundations and conceptual framework 37615.3. Data collection and preprocessing infrastructure 37915.4. ML models for credit risk assessment 38115.5. Decision support system architecture 38615.6. Alternative data sources and their applications 38815.7. Algorithmic fairness and bias mitigation 39015.8. Regulatory compliance and governance 39215.9. Case studies and empirical evidence 39415.10. Emerging trends and future directions 39615.11. Implementation challenges and practical considerations 39815.12. Conclusion 40315.13. References 404Chapter 16. 5G/6G-Enabled V2X for Intelligent Transportation Systems: AI Security Challenges and Cyber Resilience 407Meryem RHESDAOUI, Mariya OUAISSA, Mariyam OUAISSA and My Ahmed EL KIRAM16.1. Introduction 40716.2. Background on V2X and intelligent transportation systems 40916.3. 5G and 6G as enablers of AI-driven V2X 41716.4. AI security challenges in 5G/6G V2X systems 42216.5. Cyber resilience principles for AI-enabled V2X 42916.6. Conclusion 43116.7. References 432List of Authors 435Index 441

Mariya Ouaissa is an assistant professor at Cadi Ayyad University, Morocco. Her research focuses on IoT, wireless and cyber-physical security.Hemant Kumar Saini is an academic at Lincoln University College, Malaysia, and Bennett University, Greater Noida, India. His research spans IoT, wireless networks and AI.Pankaj Bhambri is a post-doctoral researcher at Lincoln University College, Malaysia, and an associate professor at GNDEC, Ludhiana, India. His research specializes in ML, bioinformatics and WSNs.Mariyam Ouaissa is an assistant professor at ENSA, Chouaib Doukkali University, Morocco. Her research focuses on IoT, wireless networks and security.

• Preface xviiMariya OUAISSA, Hemant Kumar SAINI, Pankaj BHAMBRI and Mariyam OUAISSAChapter 1. Systemic Risks in Contemporary AI Systems: Misinformation, Model Dependency and Supply-Chain Vulnerabilities 1Saba FATIMA, C. Kishor Kumar REDDY, P.R. ANISHA, Umaima Qader MOHIUDDIN and Jothi PARANTHAMAN1.1. Introduction 21.2. Literature survey 31.3. Data as a strategic asset in modern digital systems 51.4. Threat landscape: AI systems under siege 71.5. Data abuse in AI pipelines 111.6. Ethical dilemmas across the AI lifecycle 141.7. Third-party model risks 241.8. AI and digital twins under siege 271.9. Combating dark intelligence: cyber resilience framework 281.10. Results and discussion 321.11. Conclusion 321.12. References 33Chapter 2. Data Abuse, Ethics Dilemmas, Supply Chain Poisoning and Third-Party Model Risks in the Age of AI Misinformation 37Shailja TRIPATHI and Laxmi Pandit VISHWAKARMA2.1. Introduction 382.2. Nature of AI and AI misinformation 392.3. Ethical dilemma generated by AI misinformation 412.4. Strategies for reducing ethical dilemmas caused by AI misinformation 492.5. Conclusion 562.6. Limitations and future scope 572.7. References 57Chapter 3. The Data Poisoning Problem in Digital Twin Intelligence: Foundations, Risks and Probabilistic Defense Strategies 65M'kouka BTISSAM, Zahedi CHAYMAA, Mariya OUAISSA and Mariyam OUAISSA3.1. Introduction 653.2. Digital twin foundations 663.3. Data poisoning problem 683.4. Risks for digital twins 703.5. Probabilistic defense strategies 723.6. Conceptual framework for data poisoning detection in digital twins 743.7. Future directions and conclusion 773.8. References 78Chapter 4. Adversarial Exploitation Lifecycle (AEL): Unveiling Dark Intelligence and Synthetic Identity Manipulation in Cognitive Security Systems 81Bebesh TRIPATHY, Apoorwa SINGH, Parul SOOD and ANNUPRIYA4.1. Introduction 824.2. Literature review 844.3. Conceptual foundations of synthetic identity and dark intelligence 874.4. Anatomy of the adversarial exploitation lifecycle (AEL) 934.5. Emerging attack strategies on synthetic identity systems 984.6. Result and evaluation 984.7. Challenges and limitations 1024.8. Future outcomes 1024.9. Conclusion 1034.10. References 104Chapter 5. Detecting Dark Intelligence in Cyber-Physical Digital Twins Using Self-Learning AI and Cognitive Security Analytics 107Preeti CHUGH, Imene Elhachfi ESSOUSSI, BABITA, SHUBNEET and Anushka Raj YADAV5.1. Introduction and motivation 1085.2. CPDT and self-learning fundamentals 1115.3. Dark intelligence threat extraction 1145.4. Stealth attack detection in twins 1175.5. Sensor and log analysis in CPDTs 1205.6. Model poisoning classification 1225.7. Twin vulnerability assessment 1265.8. Advanced self-learning techniques 1285.9. Case studies and evaluations 1315.10. Challenges and ethical considerations 1335.11. Conclusion 1365.12. References 137Chapter 6. A Hybrid Transformer Automata Framework for Behavioral Anomaly Detection of FraudGPT and Dark LLM Threats 143Ankita PATIL, Mritunjay Kr. RANJAN, Pankaj PATIL, Nitin MALI, Rajashri RIKAME and Disha ARSUDE6.1. Introduction 1446.2. Related work 1476.3. Problem statement 1486.4. Methodology 1506.5. System architecture 1586.6. Result and discussion 1586.7. Conclusion 1636.8. Future work 1646.9. References 164Chapter 7. Trusted Twin Security Architecture (TTSA): Enabling Autonomous Risk Mitigation and Cognitive Trust in AI-Driven Digital Twin Systems 169Bebesh TRIPATHY, Sudhanshu SHARMA and Pritesh TRIPATHY7.1. Introduction 1707.2. Literature review 1727.3. Threat landscape in digital twin and autonomous systems 1767.4. Autonomous risk mitigation framework 1787.5. Fundamentals of trusted twin security architecture 1837.6. Result and evaluation 1877.7. Challenges and limitations 1907.8. Future outcomes 1907.9. Conclusion 1917.10. References 192Chapter 8. Hybrid Cognitive-Explainable AI Architecture for Proactive Cyber Defense in Multi-Layer Networks 195Vaibhav SONAJE, Pranjal SONJE, Disha ARSUDE, Rajashri RIKAME, Ankita PATIL and Mritunjay Kr. RANJAN8.1. Introduction 1958.2. Related study 1988.3. Problem statement 1998.4. Methodology 2028.5. System architecture 2108.6. Result and discussion 2108.7. Conclusion 2148.8. Future work 2148.9. References 215Chapter 9. Adaptive Cyber Resilience via Bio-Inspired Computing: An ACRF-Based Autonomous Immune-System Defense Model 219Disha ARSUDE, Mritunjay Kr. RANJAN, Ramdas GORE, Kalyani PURKAR, Ankita PATIL and Rajashri RIKAME9.1. Introduction 2209.2. Related study 2239.3. Problem statement 2259.4. Methodology 2259.5. System architecture 2379.6. Result and discussion 2389.7. Conclusion 2419.8. Future work 2429.9. References 242Chapter 10. Neuro-Cognitive ML Framework for Deepfake Detection and Spoofed Sensor Integrity in Cyber–Physical Systems 247Rajashri RIKAME, Mritunjay Kr. RANJAN, Monali JADHAV, Sarika KONDEKAR, Disha ARSUDE and Ankita PATIL10.1. Introduction 24810.2. Related study 25010.3. Problem statement 25210.4. Methodology 25210.5. System architecture 26510.6. Result and discussion 26510.7. Conclusion 26910.8. Future work 27010.9. References 270Chapter 11. Explainable ML-Based Detection of Network-Based Fuzzing Attacks 273Nadeen AHMAD, Farida EMAM, Mouza ALAMERI and Mohammed M. ALANI11.1. Introduction 27311.2. Related works 27511.3. Proposed system 28011.4. Methodology 28111.5. Results and analysis 28511.6. Discussion. 29311.7. Conclusion 29511.8. References 296Chapter 12. A Unified Framework for Decentralized and Private Verification of Wearable Health Data using Blockchain and Zero Knowledge Proofs (ZKPs) 299Anant UPADHIYAY and Abhishek JAIN12.1. Introduction 30012.2. Related work 30012.3. Life cycle of privacy-preserving verification 30312.4. System design and architecture 30512.5. Implementation details 31012.6. Cloud native integration and operational view 31512.7. Result and discussion 31812.8. Conclusion 32312.9. Future work 32412.10. References 324Chapter 13. Identity-Centric Database Security for Resilient Cloud-Based Digital Twin Infrastructure 327Aktham AL-YAHYA and Qasem Abu AL-HAIJA13.1. Introduction 32713.2. Cloud authentication mechanisms 33013.3. Access control and identity management 33413.4. Database security in cloud environments 33813.5. Malware and insider threats in cloud databases 34113.6. Case study: the Capital One data breach 34313.7. Data-driven cloud security analytics 34613.8. Conclusions and future directions 34813.9. References 349Chapter 14. Protecting Smart Grid Digital Twins from Dark Intelligence Using Firewalls and Intrusion Detection Systems 353Akram AL-DHAFARI and Qasem Abu AL-HAIJA14.1. Introduction 35314.2. Smart grid architecture and threat landscape 35614.3. Firewall technologies for smart grids 35914.4. IDS/IPS 36314.5. Cryptography and authentication in smart grids 36614.6. Case study: the Ukraine power grid attack 36814.7. Data-driven threat analytics for smart grids 37014.8. Conclusions and future directions 37214.9. References 373Chapter 15. Big Data Analytics and AI-Driven Decision Support Systems for Financial Inclusion and Microfinance Risk Assessment 375Tanvir Mahmoud HUSSEIN, Kannadasan KARUPPAIAH, Palanivel R.M., Prabu NEETHIDOSS, Wajid Ahmed ANSARI, Abdul Saleem MOHAMMED, Abdul Waheed MOHAMMED, Sivasankar PRABAHARAN and Vinoth RAMAN15.1. Introduction 37515.2. Theoretical foundations and conceptual framework 37615.3. Data collection and preprocessing infrastructure 37915.4. ML models for credit risk assessment 38115.5. Decision support system architecture 38615.6. Alternative data sources and their applications 38815.7. Algorithmic fairness and bias mitigation 39015.8. Regulatory compliance and governance 39215.9. Case studies and empirical evidence 39415.10. Emerging trends and future directions 39615.11. Implementation challenges and practical considerations 39815.12. Conclusion 40315.13. References 404Chapter 16. 5G/6G-Enabled V2X for Intelligent Transportation Systems: AI Security Challenges and Cyber Resilience 407Meryem RHESDAOUI, Mariya OUAISSA, Mariyam OUAISSA and My Ahmed EL KIRAM16.1. Introduction 40716.2. Background on V2X and intelligent transportation systems 40916.3. 5G and 6G as enablers of AI-driven V2X 41716.4. AI security challenges in 5G/6G V2X systems 42216.5. Cyber resilience principles for AI-enabled V2X 42916.6. Conclusion 43116.7. References 432List of Authors 435Index 441