Search

Browse Subject Areas

For Authors

Submit a Proposal

Disinformation Security for Generative AI Applications

Concepts, Methodologies, and Use Cases
Edited by T. Ananth Kumar, S. Balakrishnan, S. Aasha Nandhini, M. Satheesh Kumar and S. Balamurugan
Series: Leading-Edge Breakthroughs in Artificial Intelligence
Copyright: 2026   |   Expected Pub Date:2026/10/30
ISBN: 9781394422364  |  Hardcover  |  
508 pages

One Line Description
This book is an essential roadmap for AI researchers, security analysts, and policymakers, delivering actionable, cross-cutting frameworks to defend democratic institutions and digital ecosystems against the growing threat of AI-driven disinformation.

Audience
AI researchers, machine learning engineers, cybersecurity professionals, data scientists, academics, and policymakers working on generative models, adversarial robustness, AI-driven threats, synthetic media, and digital forensics.

Description
Generative artificial intelligence (AI) has ushered in a new era of content creation, enabling unprecedented capabilities in text, image, and video synthesis. However, these advancements come with significant risks, particularly the potential for AI to be exploited for disinformation. From deepfakes and synthetic text to AI-powered social engineering and adversarial attacks, malicious uses of generative AI pose serious threats to individuals, institutions, and democratic societies. Unlike traditional approaches that treat disinformation as a media or policy problem, this book frames it as a complex socio-technical security issue. It presents a layered perspective on disinformation threats, integrating advances in generative AI with detection strategies, policy frameworks, and ethical considerations. From adversarial machine learning and provenance tracking to explainable AI and decentralized content authentication, the book introduces cross-cutting methodologies to secure digital ecosystems against manipulation at scale.
At the heart of the book is the recognition that generative AI is both a tool and a threat. It can democratize creativity and intelligence, but without strong governance, it can just as easily erode truth, exploit biases, and amplify social discord. This duality is addressed through real-world use cases spanning sectors like journalism, healthcare, energy systems, and finance, where disinformation poses not just reputational risks but systemic vulnerabilities. The book highlights how technical innovation must be accompanied by transparency protocols, regulatory mechanisms, and ethical design to build societal resilience.
Readers will find the book:
• Bridges theory and practice by combining foundational concepts with real-world case studies across healthcare, media, engineering, and energy;
• Covers the full threat landscape of generative AI, including deepfakes, synthetic text, adversarial attacks, and AI-powered social engineering;
• Presents actionable methodologies for detection, mitigation, watermarking, and provenance tracking of AI-generated content;
• Addresses ethical, regulatory, and governance frameworks, making it ideal for interdisciplinary audiences.

Back to Top
Author / Editor Details
T. Ananth Kumar, PhD is an Associate Professor Department of Computer Science and Engineering, IFET College of Engineering, Tamil Nadu, India. He has authored one book, several book chapters, and various papers in national and international conferences and journals.

S. Balakrishnan, PhD is a Professor and Head of the Department of Computer Science and Engineering, Vinayaka Mission’s Research Foundation University, Paiyanoor, Chennai, India. He has published more than 39 books, ten book chapters, and more than 150 publications in highly cited journals and conferences.

S. Aasha Nandhini, PhD is an Assistant Professor in the Department of Electronics and Communication Engineering, Sri Sivasubramaniya Nadar College of Engineering, Chennai, India. She has published two books, six book chapters, and twelve publications in reputed international journals and conferences, and holds a granted patent.

M. Satheesh Kumar, PhD is an Associate Principal of Cybersecurity at LTI Mindtree with more than 17 years of experience in the cybersecurity industry. He has published five journal articles, four book chapters, and one patent. His research interests include malware analysis, network security, and cyber forensics.

S. Balamurugan, PhD is the Director of Research at iRCS, an Indian Technological Research and Consulting Firm in Coimbatore, Tamil Nadu. He has published 75 books, 300 papers in international journals and conferences, and 300 patents. With 20 years of research on various cutting-edge technologies, he provides expert guidance in technology forecasting and decision making for leading companies and startups.

Back to Top

Table of Contents
Series Preface
Preface
Part 1: Foundations and Advances in Generative AI and Machine Learning
1. Recent Advances in Generative Modeling: A Unified Review
of GANs, Transformers, Autoencoders, Diffusion Models, and Large Language Architectures
S. Tamil Selvi and P. Visalakshi
1.1 Introduction
1.2 Generative Models
1.3 GAI Task and Tools
1.4 Industrial Application of GIA
1.5 Challenges of GAI
1.6 The Future of GAI
1.7 Conclusion
References
2. Machine Learning for Fake Content Detection—Developing
Classifiers and Anomaly Detection for AI-Generated Text, Images, and Videos
Naveenkumar M., Vidhya Saraswathy S. S. and Srinathi B.
2.1 Introduction
2.1.1 Conventional Methods Used in Fake Content Detection
2.1.2 Modern Generation of Fake Content Detection
2.1.3 Objective
2.1.4 Problem Statement
2.1.5 Chapter Outline
2.2 Related Work
2.2.1 Introduction
2.2.2 Text-Based Misleading Content
2.2.2.1 Fake News
2.2.2.2 Clickbait
2.2.2.3 Fake Reviews
2.2.3 Visual Fake Content
2.2.3.1 Memes
2.2.3.2 Altered Photographs
2.2.4 Fake Audio and Video Content
2.2.4.1 Deepfakes
2.2.4.2 Synthetic Speech
2.2.5 Multimodal Misinformation
2.3 Methodology
2.3.1 Data Collection and Preprocessing
2.3.2 Sources of Fake and Real Data
2.3.3 Data-Labeling Strategies
2.3.4 Data Cleaning Techniques
2.3.5 Preprocessing Techniques
2.3.5.1 Text Preprocessing
2.3.5.2 Image and Video Preprocessing
2.3.5.3 Audio Preprocessing
2.3.6 Handling Class Imbalance
2.3.7 Tools and Frameworks
2.4 Feature Engineering
2.4.1 Introduction
2.4.2 Textual Features
2.4.2.1 Linguistic and Syntactic Features
2.4.2.2 Bag of Words (BoW) and TF-IDF
2.4.2.3 N-Grams
2.4.2.4 Readability Scores
2.4.2.5 Named Entity Recognition (NER)
2.4.3 Visual Features
2.4.3.1 Image Metadata
2.4.3.2 Pixel-Level Features
2.4.3.3 Facial Landmarks (for Deepfakes)
2.4.4 Behavioral Features
2.4.4.1 User Posting Behavior
2.4.4.2 Network Patterns and Source Credibility
2.4.5 Integration of Features for Robust Models
2.4.5.1 Multimodal Fusion Techniques
2.4.5.2 Ensemble Learning
2.4.5.3 Real-Time Implementation Challenges
2.5 Machine Learning Techniques
2.5.1 Introduction
2.5.2 Traditional Machine Learning Algorithms
2.5.2.1 Naïve Bayes
2.5.2.2 Logistic Regression
2.5.2.3 Support Vector Machines (SVMs)
2.5.2.4 Random Forests
2.5.2.5 Gradient Boosting
2.5.3 Feature Selection Techniques
2.5.3.1 Chi-Square Test (X2)
2.5.3.2 Mutual Information
2.5.3.3 PCA (Principal Component Analysis)
2.6 Deep Learning Techniques: Ways Machines Learn Similar to Us Humans
2.6.1 Sequence Learning: RNNs, LSTMs, and GRUs
2.6.2 Seeing the World—Convolutional Neural Networks (CNNs)
2.6.3 Language Understanding-Transformers Models
2.6.4 Create and Detect—GAN (Generative Adversarial Network)
2.6.5 Multi-Modal Learning (Combining Text, Image, and Metadata)
2.7 Result and Discussion
2.7.1 Fake Content Detection Pipelines
2.7.2 Tools and Frameworks
2.8 Evaluation Metrics
2.8.1 Definitions of Evaluation Metrics Accuracy
2.8.2 Confusion Matrix
2.8.3 Classification Report (Heatmap)
2.8.4 ROC Curve and AUC
2.8.5 Precision-Recall Curve
2.8.6 Learning Curve
2.8.7 Overall Interpretation
2.8.8 Domain-Specific Challenges in Evaluation
2.9 Case Studies and Real-World Application
2.9.1 Facebook, Twitter, and YouTube: Fake Content Moderation
2.9.2 Fact-Checking Platforms
2.9.3 E-Commerce Fake Review Detection
2.9.4 Government and Legal Considerations
2.10 Challenges and Limitations
2.10.1 Evolving Nature of Fake Content
2.10.2 Adversarial Attacks and Model Robustness
2.10.3 Bias in Training Data
2.10.4 Challenges of Multilingualism and Cross-Domainism
2.10.5 Computational and Infrastructure Requirements
2.11 Conclusion and Future Scope
References
3. A Transformer-Based Hybrid Machine Learning Approach for Detecting AI-Generated Misinformation
R. Pari, Likhith Muthavarapu, Parvinder Kaur, Anurag Reddy Ekkati, P. Lakshmi Prasanna and P. Jeyabharathi
3.1 Introduction
3.2 Literature Review
3.3 Overview of AI-Generated Misinformation
3.3.1 Types of AI-Generated Misinformation
3.3.2 How AI-Generated Misinformation Spreads
3.4 Proposed Hybrid Machine Learning Approach
3.4.1 Data Collections
3.4.2 Text Processing
3.4.3 Feature Extraction Phase
3.4.4 Hybrid Model Training and Classification
3.5 Experimental Setup
3.5.1 Hardware and Software Configurations
3.5.2 Dataset Preparation
3.5.3 Model Training Strategy
3.5.4 Performance Measurement
3.6 Results Analysis and Discussion
3.6.1 Confusion Matrix Analysis
3.6.2 Comparative Performance Analysis of Classification Models
3.7 Conclusion and Future Enhancement
References
Part 2: Generative AI Applications in Healthcare and Biomedical Domains
4. Utilizing Generative AI and Foundation Models to Personalize Healthcare: Predictive Analytics and Customized Treatment Plans via Cascaded Deep Capsule Neural Networks
N. Naveenkumar, Seshukumar, J. Jude Moses Anto Devakanth,
S. Balamurugan, P. Hanok and Deepthidotla
4.1 Introduction
4.2 Literature Survey
4.2.1 Problem Statement
4.3 Proposed Methodology
4.3.1 Input Collection
4.3.2 Correlation Coefficients with Min–Max Normalization–Based Preprocessing
4.3.3 Cascaded Deep Capsule Neural Networks with Multi-Axis Vision Transformer (CDBNN-MVT)
4.3.4 MaxViT Block
4.3.5 Banyan Tree Growth Optimization
4.4 Results and Discussions
4.5 Conclusion
References
5. Generative AI-Driven Patient Twins: Transforming Precision and Predictive Healthcare
Rajeswari R. and Kiruba Kumari
5.1 Introduction
5.2 Fundamentals of Generative AI
5.3 Foundations of DTs in Medicine
5.3.1 Different Types of Digital-Twin Technology
5.3.2 Working of Digital Twin
5.4 AI-Generated Patient Twins: A Conceptual Framework
5.5 The Role of Generative AI in Patient Twin Development
5.5.1 Generative AI Powers Patient Twin Development
5.6 Applications of DT in Clinical Practice
5.6.1 Building Individualized Treatment Programs
5.6.2 Virtual Surveillance of Patients
5.6.3 Digital Clinical Investigations
5.6.4 DT in Hospital Management
5.6.5 Analytics and Disease Progression Modeling
5.7 Seven Integration into Precision and Predictive Medicine
5.7.1 Framework of Digital Twins
5.7.2 Potential Applications of Digital Twins in Medicine
5.7.3 Prediction
5.7.4 Precision Medicine
5.8 Challenges in Implementing Digital Identical Twin in Healthcare
5.8.1 Reality
5.8.2 Ethics
5.8.3 Global Adoption of Digital Twin Tools in Vital Support
5.8.4 Strategies for Successful Implementation
5.9 Future Directions: Toward Real-Time Adaptive Healthcare
5.10 Conclusion
References
6. Role of AI in Accurate and Disinformation-Resilient Diagnosis of Ulcerative Colitis
Latha D., Lakshmi D., Mohana R. and Nithiya A.
6.1 Introduction
6.2 Related Works
6.3 Methodology
6.4 Result and Discussion
6.5 Conclusion
References
7. A Generative AI Framework for Predicting Shear Strength
Properties of Rock Materials Using ISSA-XGBoost
Tamilselvi. P.
7.1 Introduction
7.2 Understanding Generative AI
7.2.1 Core Technologies Behind Gen-AI
7.3 An Introduction to Rock Minerals
7.3.1 Importance of Rock Minerals
7.3.2 How Geological Data are Collected
7.4 Integration of Generative AI in Geological Survey and Mineral Targeting
7.4.1 Applications in Mineral Exploration
7.5 Gen-AI Algorithm to Discover the Rock Structure
7.5.1 Support Vector Machine (SVM)
7.5.2 Decision Trees and Random Forest in Rock Mass Classification
7.5.3 Extreme Gradient Boosting (XGBoost)
7.5.4 Genetic Algorithm
7.5.5 Strong Deep Learning Algorithms: Recurrent Neural Networks/LSM
7.6 Rock Structure Datasets
7.6.1 Observations of USGS Rock Mass Quality and Structural Geology
7.6.2 The Geochemistry of Oceanic and Continental Rocks is Known as GEOROC
7.6.3 Portal for Digital Rocks
7.6.4 DRP-372: Dataset of 3D Structural and Simulated Transport Properties
7.6.5 Ocean Floor Petrological Database (PetDB)
7.6.6 Sample Data Schema for Rock Strength Prediction
7.7 Rock Mechanics Applications
7.7.1 AI-Driven Rock Mass Classification in Tunneling
7.7.2 Graph Neural Networks for Predicting Rock Elastic Moduli
7.7.3 Phase Field Modeling of Brittle Fractures
7.7.4 Hydropower Tunneling in Challenging Geologies
7.7.5 Rock Mechanics in Petroleum and Natural Gas Engineering
7.7.6 Geo-Energy Applications: Carbon Sequestration and Geothermal Systems
7.7.7 Optimizing Hydraulic Fracturing in Mining
7.7.8 Advancements in Nuclear Waste Repository Design
7.8 Conclusion
7.9 Future Work
References
Part 3: AI and Disinformation — Security, Detection, and Mitigation
8. Sign Language Recognition in the Age of AI with Disinformation Risks and Security Solutions
T. Grace Shalini, Sayed Sayeed Ahmad, Mrinalini Vaish, Neelansh Bhargava, Krishikaa Mathi Bharathi S. S. and Karthick Manoj. R.
8.1 Introduction
8.2 Literature Survey
8.3 Research Gap
8.4 Proposed Methodology
8.4.1 System Architecture
8.4.2 Modules and Data Flow
8.4.3 Model Design and Training
8.5 Comparative Study and Tool Justification
8.6 Advantages Over Existing Systems
8.7 Results
8.8 Future Enhancements
8.9 Conclusion
References
9. EmoFusionNet: A Cutting-Edge Framework for Emotion Propagation with Attention-Enhanced Hypergraphs and Generative Temporal Forecasting
G. Akiladevi, M. Arun and J. Palanimeera
9.1 Introduction
9.1.1 Sentiment Analysis
9.1.2 Machine Learning Strategies
9.1.3 Graph Neural Networks
9.2 Temporal Graph Neural Networks
9.3 Literature Review
9.3.1 Deep Learning–Based Approaches
9.4 Methodology
9.4.1 Dataset
9.4.2 Activity-Driven Time-Evolving Network Description
9.4.3 Prediction of Event Time
9.4.4 HNN
9.4.4.1 Attention Network
9.4.5 Conditional Generative Adversarial Network (CGAN) with LSTM
9.4.5.1 The Generator
9.4.5.2 The Discriminator
9.4.6 Long Short-Term Memory Neural Network
9.5 Conclusion
References
10. Advancing Trustworthy Content Verification through
Explainable AI for Disinformation Mitigation
Barakkath Nisha U., Yasir Abdullah R., Anantraj I., Mary Posonia A. and Ram Shivany K.
10.1 Introduction
10.2 Theoretical Foundations
10.3 Techniques for Explainable AI
10.4 Architectures for Trustworthy Verification
10.5 Evaluating Trust and Explainability
10.6 Experimental Results and Analysis
10.6.1 Dataset and Experimental Setup
10.6.2 Quantitative Evaluation of Trust Metrics
10.7 Use Cases and Real-World Scenarios
10.7.1 News Media Verification: Fact-Checking Synthetic Text
10.7.2 Legal and Policy Domains: Document Consistency and Authenticity
10.7.3 Healthcare and Science: Verification of AI-Generated Clinical or Academic Content
10.7.4 AI-Assisted Journalism: Maintaining Editorial Integrity with GenAI Tools
10.8 Cross-Domain Trust Transferability
10.8.1 Generalizing Trust Scores Across Domains
10.8.2 Risks of Domain Shift and Content Drift
10.8.3 Evaluating Cross-Domain Adaptability
10.9 Human-AI Interaction and Trust Calibration
10.9.1 Human Interpretability Thresholds vs. System Fidelity
10.9.2 Overtrust, Undertrust, and Cognitive Bias in Explanations
10.9.3 Interface Design for Trust-Sensitive Tasks
10.10 Policy, Regulation, and Ethical Mandates
10.10.1 Global Regulatory Frameworks
10.10.2 The Role of Governments and Institutions in Mandating XAI
10.10.3 Explainability as an Ethical Obligation in Public Systems
10.11 Building Future-Ready Verification Frameworks
10.11.1 Lifelong Learning and Explainability in Dynamic Systems
10.11.2 Edge-AI and Federated Verification Systems
10.11.3 Interoperability and Cross-Platform API Standards
10.12 Challenges and Research Directions
10.12.1 Trade-Off Between Performance and Interpretability
10.12.2 Verification in Multimodal and Multilingual Content
10.12.3 Ethical Risks and Algorithmic Biases in XAI
10.12.4 Need for Unified Frameworks and Standardization
10.12.5 Future Outlook: Trusted GenAI in Regulated Domains
10.12.6 Conclusion
References
11. Detecting Deepfakes in Generative Media with an Explainable CNN‑Transformer Approach
R. Karthick Manoj, M. Arul Pugazhendhi, K. Suresh Kumar and Sunday Adeola Ajagbe
11.1 Introduction
11.1.1 The Rise of Deepfakes and Generative Disinformation
11.1.2 Limitations of Traditional Detection Methods
11.1.3 The Need for Explainable Artificial Intelligence (XAI)
11.1.4 Generative AI and the Evolving Threat Landscape
11.1.5 XAI in Deepfake Detection Pipelines: Opportunities and Challenges
11.1.6 Societal and Regulatory Imperatives
11.1.7 Deepfake Detection Landscape
11.1.8 The Role of XAI in Deepfake Detection
11.2 Methodology
11.2.1 System Overview
11.2.2 Dataset Description
11.2.3 Deepfake Classifier Models
11.2.4 Explainability Layer
11.2.5 Evaluation Metrics
11.3 Results and Visualization
11.3.1 Classification Performance
11.3.2 Explainability Performance
11.4 Conclusion
References
12. Analysis of Sentiment in Tamil Comments Using BERT and Explainable AI
N. Priyadharshini and N. Subbulakshmi
12.1 Introduction
12.1.1 Different Methodologies in Sentiment Analysis
12.1.1.1 Supervised Learning
12.1.1.2 Unsupervised Learning Methods
12.1.1.3 Hybrid Method
12.1.2 Levels of Sentiment Analysis
12.1.2.1 Word-Level Analysis
12.1.2.2 Sentence-Level Analysis
12.1.2.3 Aspect-Based Analysis
12.1.2.4 Document-Level Analysis
12.2 Literature Survey
12.3 Datasets Availability
12.4 Dataset Used
12.5 Preprocessing
12.5.1 Normalization of Text
12.5.2 Elimination or Mapping of Emoji and Special Symbols
12.5.3 Spelling Variations
12.5.4 Slang Standardization
12.5.5 Stop Word Filtering
12.5.6 Label Encoding
12.5.7 Tokenization Challenges in Tamil
12.5.7.1 Tokenization
12.5.8 Example for Input Text Preprocessing
12.6 Constructing a Tamil Sentiment Lexicon
12.6.1 Integrating Lexicon Scores with Deep Models
12.7 Handling Code-Mixed Tamil-English Text
12.8 Methodologies
12.8.1 Lexicon-Based Analysis
12.8.2 Explainable AI (LIME) Analysis
12.8.2.1 The Importance of Interpretability in NLP
12.8.2.2 Why LIME was Chosen
12.8.2.3 How LIME Explains Predictions in the Tamil Sentiment Model
12.8.2.4 Explainable AI Integration
12.8.2.5 Example Output for the XML-R (LIME)
12.9 Results and Evaluation
12.9.1 Comparison BERT without Lexicon vs. BERT + Lexicon Integration
12.9.2 IndicBERT vs. XLM-RoBERTa
12.10 Cross-Lingual Transfer and Challenges
12.11 Case Studies
12.12 Future Works
12.12.1 Larger Domain-Specific Lexicons
12.12.2 LLM-Based Zero-Shot and Few-Shot Approaches
12.12.3 Using SHAP for Better Visual Explanations
12.13 Conclusion
References
13. Securing Generative AI Against Disinformation in Low-Stability Renewable Power Networks
R. Rajasree, D. Lakshmi, K. Stalin and R. Karthick Manoj
13.1 Introduction
13.1.1 Adoption of Generative AI in Renewable Energy Systems
13.1.2 Disinformation as a Security Threat in AI Applications
13.1.3 Risks of Disinformation in Renewable Energy Operation
13.1.4 Emerging Threat of Disinformation in AI Systems
13.1.5 Importance of Security and Integrity in AI-Driven Energy Forecasting
13.2 Literature Survey
13.3 Proposed Methodology
13.3.1 Identification of Potential Mission Scenarios
13.3.2 Assess of Microgrid Energy Resilience to Supply Critical Loads
13.3.3 Added Distributed Energy Resources or Storage
13.3.4 Design of Microgrid
13.3.5 Energy Resilience
13.4 Results and Discussion
13.5 Conclusion
References
Part 4: AI in Sustainable Development, Agriculture, and Smart Systems
14. Securing Agricultural IoT Systems Against Disinformation
for Sustainable Rural Development
S. Murugesan, S. Ramalingam, P. Usharani and P. Kanimozhi
14.1 Introduction
14.2 Literature Review
14.2.1 Problem Statement
14.3 Proposed Methodology
14.3.1 Data Collection
14.3.2 Cleaning and Preparing of Data
14.3.3 Feature Selection
14.3.4 Content Centric Network (CCN)
14.4 Results and Discussions
14.4.1 Performance Metrics
14.4.2 RMSE, MAE, MAPE, and R-Squared Analysis
14.5 Conclusion
References
15. Resilient Embodied AI for Smart Farming: Tackling Misinformation in Bioacoustic Pest Detection
T. Grace Shalini, Sayed Sayeed Ahmad, Nayantra Ramakrishnan, Bhavesh P. and Karthick Manoj R.
15.1 Introduction
15.2 Literature Survey
15.3 Research Gaps
15.4 Proposed Methodology
15.4.1 Acoustic Sensing and Signal Acquisition Layer
15.4.2 Feature Extraction and Deep Learning Classification Layer
15.4.3 Embodied Navigation and Path Optimization Layer
15.4.4 Cognitive Decision and Control Layer
15.4.5 Feedback Loop and Adaptive Learning Engine
15.4.6 Cloud Analytics and Visualization Dashboard
15.5 Comparative Study and Tool Justification
15.6 Advantages Over Existing Systems
15.7 Future Enhancements
15.8 Conclusion
References
16. CNN-GA: Pose Recognition Using Region-Based Convolutional Neural Networks and Genetic Algorithm
J. Palanimeera, K. Ponmozhi and G. Akiladevi
16.1 Introduction
16.1.1 History of Yoga
16.1.2 Benefits of Yoga
16.1.3 Effects of Wrong Yoga Posture
16.1.4 Monitored Practice and Correct Alignment
16.1.4.1 Monitored Practice
16.1.4.2 Correct Alignment
16.1.5 Computer Vision and Human Pose Estimation
16.1.6 Deep Learning in Pose Classification
16.2 Related Works
16.2.1 Multi-Person Pose Estimation
16.2.2 Review of Pose Recognition Using Deep Learning Models
16.2.2.1 DeepPose
16.2.2.2 OnePose
16.2.2.3 Stacked Hourglass Networks
16.2.2.4 HRNet
16.2.2.5 PoseNet
16.2.2.6 Graph Convolutional Networks
16.3 Methodology
16.4 Experimental Results
16.5 Discussion
16.6 Conclusion
References
Index

Back to Top



Description
Author/Editor Details
Table of Contents
Bookmark this page