I. Eugene Berna
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
I. Eugene Berna has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Vijay Kandasamy
Rajalakshmi Engineering College
9 shared publications - Jeyalakshmi Jeyabalan
Amrita School of Computing, India
3 shared publications - Ravikumar Subburam
Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai, India
3 shared publications - Gnanavel Sakkarvarthi
Department of Computing Technologies, School of Computing, SRM Institute of Science and Technology, Kattankulathur, India
2 shared publications - Arockia Raj Y.
PSNA College of Engineering and Technology, Dindigul, India
1 shared publication - Athiraja Atheeswaran
Department of Computer Science and Engineering (Cyber Security) Saveetha Engineering College Chennai India
1 shared publication
Latest Publications
- 11 October 2026
- Published by Wiley in Computational Intelligence
- Vol. 42 (5) , e70298
Federated Attention‐Augmented Hybrid Framework for Real‐Time Intrusion Detection in Cloud Environments: Integrating Transformer‐Enhanced Convolutional Networks With Privacy‐Preserving Stochastic Optimization
The widespread adoption of cloud services in government and commercial environments has enlarged the attack surface exposed to advanced persistent threats, zero‐day exploits, and polymorphic distributed denial‐of‐service attacks. This paper presents the Federated Attention‐Augmented Hybrid Intrusion Detection Framework (FAAHIDF), which couples four established components through one training and deployment protocol: a Multi‐Head Spatial Attention Convolutional Encoder (MHSACE), a Federated Differential‐Privacy Stochastic Gradient Descent Optimizer (FDP‐SGDO), a Cross‐Domain Normalization and Augmentation Engine (CDNAE), and a Dynamic Threshold Calibration Module (DTCM). The contribution is therefore the coordinated interaction among local–global representation learning, privacy‐bounded federated updating, target‐aware domain alignment, and drift‐responsive decision calibration, rather than novelty of each primitive in isolation. CSE‐CIC‐IDS2018 is used as the labeled source benchmark. For UNSW‐NB15, only an unlabelled target‐development partition is exposed to CDNAE, whereas the held‐out target evaluation subset is excluded from normalization fitting, augmentation, domain alignment, threshold selection, and hyperparameter tuning; this experiment is consequently reported as target‐aware unsupervised domain adaptation rather than a fully unseen external test. Under the fixed experimental configuration, FAAHIDF records 99.87% accuracy, a 0.02% false‐positive rate, 0.9998 AUC, and 0.9981 macro‐F1 on CSE‐CIC‐IDS2018, and 98.74% accuracy with 0.9841 macro‐F1 on the held‐out UNSW‐NB15 target subset. These values are treated as point estimates. The revised manuscript limits statistical and state‐of‐the‐art claims to the available evidence, clarifies the cumulative privacy configuration (epsilon = 2.50, delta = 1e‐5), and adds module‐wise computational, communication, leakage‐control, baseline‐scope, and reproducibility analyses.
- 11 October 2026
- Published by Wiley in Computational Intelligence
- Vol. 42 (5) , e70298
Federated Attention‐Augmented Hybrid Framework for Real‐Time Intrusion Detection in Cloud Environments: Integrating Transformer‐Enhanced Convolutional Networks With Privacy‐Preserving Stochastic Optimization
The widespread adoption of cloud services in government and commercial environments has enlarged the attack surface exposed to advanced persistent threats, zero‐day exploits, and polymorphic distributed denial‐of‐service attacks. This paper presents the Federated Attention‐Augmented Hybrid Intrusion Detection Framework (FAAHIDF), which couples four established components through one training and deployment protocol: a Multi‐Head Spatial Attention Convolutional Encoder (MHSACE), a Federated Differential‐Privacy Stochastic Gradient Descent Optimizer (FDP‐SGDO), a Cross‐Domain Normalization and Augmentation Engine (CDNAE), and a Dynamic Threshold Calibration Module (DTCM). The contribution is therefore the coordinated interaction among local–global representation learning, privacy‐bounded federated updating, target‐aware domain alignment, and drift‐responsive decision calibration, rather than novelty of each primitive in isolation. CSE‐CIC‐IDS2018 is used as the labeled source benchmark. For UNSW‐NB15, only an unlabelled target‐development partition is exposed to CDNAE, whereas the held‐out target evaluation subset is excluded from normalization fitting, augmentation, domain alignment, threshold selection, and hyperparameter tuning; this experiment is consequently reported as target‐aware unsupervised domain adaptation rather than a fully unseen external test. Under the fixed experimental configuration, FAAHIDF records 99.87% accuracy, a 0.02% false‐positive rate, 0.9998 AUC, and 0.9981 macro‐F1 on CSE‐CIC‐IDS2018, and 98.74% accuracy with 0.9841 macro‐F1 on the held‐out UNSW‐NB15 target subset. These values are treated as point estimates. The revised manuscript limits statistical and state‐of‐the‐art claims to the available evidence, clarifies the cumulative privacy configuration (epsilon = 2.50, delta = 1e‐5), and adds module‐wise computational, communication, leakage‐control, baseline‐scope, and reproducibility analyses.
- 21 February 2026
- Published by Springer Nature
- p. 41-55
Quantum Federated Learning for Climate and Environmental Science
- 21 February 2026
- Published by Springer Nature
- p. 41-55
Quantum Federated Learning for Climate and Environmental Science
- 17 February 2026
- Published by Springer Nature
- p. 139-153
Human–Machine Cooperation in Data Fabric Driven by Learning
- 17 February 2026
- Published by Springer Nature
- p. 139-153
Human–Machine Cooperation in Data Fabric Driven by Learning
- 10 January 2026
- Published by Springer Nature
- p. 336-352
Enhanced Food Inflation Forecasting: An Implementation Analysis of Decision Tree Forest and Random Forest Algorithms
- 10 January 2026
- Published by Springer Nature
- p. 336-352
Enhanced Food Inflation Forecasting: An Implementation Analysis of Decision Tree Forest and Random Forest Algorithms
- 28 November 2025
- Published by IGI Global Scientific Publishing
- p. 71-96
Network Protection in Healthcare Environments
As healthcare institutions incorporate digital innovations, connected gadgets and data-driven services have complicated and networked patient care. Communication between WMDs, hospital systems, cloud platforms, and remote monitoring technologies that send sensitive patient data requires healthcare network security. Connectivity boosts creativity but adds risk. This chapter covers hospital network and WMD integration defenses against ransomware, MITM, illegal access, DoS, and APT. Zero-trust architectures, IDS/IPS, segmentation, and E2E encryption are essential because breaches jeopardize lives and compliance. Anomaly detection using SDN, NFV, and AI/ML is also examined. HIPAA and ISO/IEC 27001 demonstrate network security. Policy, governance, and personnel training are resilient system priorities. The chapter discusses dangers, remedies, and industry benchmarks to improve hospital network security.
- 28 November 2025
- Published by IGI Global Scientific Publishing
- p. 71-96
Network Protection in Healthcare Environments
As healthcare institutions incorporate digital innovations, connected gadgets and data-driven services have complicated and networked patient care. Communication between WMDs, hospital systems, cloud platforms, and remote monitoring technologies that send sensitive patient data requires healthcare network security. Connectivity boosts creativity but adds risk. This chapter covers hospital network and WMD integration defenses against ransomware, MITM, illegal access, DoS, and APT. Zero-trust architectures, IDS/IPS, segmentation, and E2E encryption are essential because breaches jeopardize lives and compliance. Anomaly detection using SDN, NFV, and AI/ML is also examined. HIPAA and ISO/IEC 27001 demonstrate network security. Policy, governance, and personnel training are resilient system priorities. The chapter discusses dangers, remedies, and industry benchmarks to improve hospital network security.
- 15 August 2025
- Published by IGI Global Scientific Publishing
- p. 181-208
Generative AI in Visual Media for Image, Video, and Animation Generation
Generative artificial intelligence (AI) technologies are fundamentally transforming the visual media landscape and automating the production of human-like images, videos, and animations. The key elements of this creation are transformer-based models, Variational AutoEncoders (VAEs), and Generative Adversarial Networks (GANs). This chapter will look at how they function, what they can be used for, and how they affect education, entertainment, and advertising. By looking closely at these methods, the chapter emphasizes both the good things that generative AI does to improve the quality and speed of content creation and the bad things that it causes in society and ethics, especially when it comes to authenticity and authorship. It also touches on the potential for misuse (think deepfakes) and discusses regulatory and ethical frameworks that would chain these technologies so that they can be used responsibly. The chapter ends with a future-oriented analysis of the emerging trends and challenges that will continue to impact the landscape of generative AI in visual media.
- 15 August 2025
- Published by IGI Global Scientific Publishing
- p. 181-208
Generative AI in Visual Media for Image, Video, and Animation Generation
Generative artificial intelligence (AI) technologies are fundamentally transforming the visual media landscape and automating the production of human-like images, videos, and animations. The key elements of this creation are transformer-based models, Variational AutoEncoders (VAEs), and Generative Adversarial Networks (GANs). This chapter will look at how they function, what they can be used for, and how they affect education, entertainment, and advertising. By looking closely at these methods, the chapter emphasizes both the good things that generative AI does to improve the quality and speed of content creation and the bad things that it causes in society and ethics, especially when it comes to authenticity and authorship. It also touches on the potential for misuse (think deepfakes) and discusses regulatory and ethical frameworks that would chain these technologies so that they can be used responsibly. The chapter ends with a future-oriented analysis of the emerging trends and challenges that will continue to impact the landscape of generative AI in visual media.
- 24 March 2025
- Published by Springer Nature
- p. 199-208
Detection of Medicinal Plants Using Machine Learning
- 24 March 2025
- Published by Springer Nature
- p. 199-208
Detection of Medicinal Plants Using Machine Learning
- 29 March 2024
- Published by IGI Global Scientific Publishing
- p. 330-350
Smart Cities and Urban Sustainability With AI
Artificial intelligence (AI) is revolutionizing urban settings by improving traffic management, energy efficiency, waste reduction, and recycling. AI-powered traffic management systems improve urban mobility, optimize traffic signals, and reduce congestion. It also optimizes waste creation and promotes recycling, improving resource management. AI-driven environmental monitoring apps monitor pollution levels in real-time, allowing proactive measures to reduce environmental impact. AI also analyzes critical infrastructure assets, enhancing public services and quality of life. However, challenges arise, such as data privacy and security, algorithmic bias, and the digital divide. To achieve AI's sustainable potential, public understanding and acceptance, regulatory and ethical standards must be addressed. By addressing these challenges, cities can create smarter, more sustainable, and people-first cityscapes.
- 29 March 2024
- Published by IGI Global Scientific Publishing
- p. 330-350
Smart Cities and Urban Sustainability With AI
Artificial intelligence (AI) is revolutionizing urban settings by improving traffic management, energy efficiency, waste reduction, and recycling. AI-powered traffic management systems improve urban mobility, optimize traffic signals, and reduce congestion. It also optimizes waste creation and promotes recycling, improving resource management. AI-driven environmental monitoring apps monitor pollution levels in real-time, allowing proactive measures to reduce environmental impact. AI also analyzes critical infrastructure assets, enhancing public services and quality of life. However, challenges arise, such as data privacy and security, algorithmic bias, and the digital divide. To achieve AI's sustainable potential, public understanding and acceptance, regulatory and ethical standards must be addressed. By addressing these challenges, cities can create smarter, more sustainable, and people-first cityscapes.
- 29 March 2024
- Published by IGI Global Scientific Publishing
- p. 64-84
Autonomous Drones and Their Integration With AI Technologies
Artificial intelligence integration in autonomous drones has various advantages, including greater operational efficiency and cost savings. By automating historically manual tasks, drones can complete them far more quickly, accurately, and cheaply than humans could. Prioritizing safety is of paramount importance when operating drones. Advanced safety measures, including real-time monitoring and collision avoidance systems, are built into AI-powered drones, making them safer to operate and reducing the likelihood of mishaps. Autonomous drones that use AI have a lot of promise, but there are a lot of problems that need fixing first. One of the key concerns is the creation of robust AI algorithms capable of adapting to dynamic situations and efficiently dealing with unforeseen scenarios. The integration of self-driving drones and AI technologies could revolutionize various sectors and enhance our everyday lives. Request access from your librarian to read this chapter's full text.
- 29 March 2024
- Published by IGI Global Scientific Publishing
- p. 64-84
Autonomous Drones and Their Integration With AI Technologies
Artificial intelligence integration in autonomous drones has various advantages, including greater operational efficiency and cost savings. By automating historically manual tasks, drones can complete them far more quickly, accurately, and cheaply than humans could. Prioritizing safety is of paramount importance when operating drones. Advanced safety measures, including real-time monitoring and collision avoidance systems, are built into AI-powered drones, making them safer to operate and reducing the likelihood of mishaps. Autonomous drones that use AI have a lot of promise, but there are a lot of problems that need fixing first. One of the key concerns is the creation of robust AI algorithms capable of adapting to dynamic situations and efficiently dealing with unforeseen scenarios. The integration of self-driving drones and AI technologies could revolutionize various sectors and enhance our everyday lives. Request access from your librarian to read this chapter's full text.
- 2 February 2024
- Published by IGI Global Scientific Publishing
- p. 34-58
Impact of Artificial Intelligence and Machine Learning in Cloud Security
The rapid advancement of artificial intelligence (AI) and machine learning (ML) technologies has had a significant impact on cloud security, as it has in many other sectors. This abstract examines how AI and ML are affecting cloud security, highlighting their major contributions, difficulties, and potential. Traditional approaches to cloud security provide improved threat detection, real-time monitoring, and adaptive defense mechanisms. These technologies are adept at processing enormous volumes of data, allowing them to spot trends, anomalies, and potential dangers that more traditional security measures would miss. In order to quickly identify and take appropriate action in response to unauthorised access, data breaches, and other malicious activities, AI-driven systems can quickly analyse user behaviour, network behaviour, and system logs. It introduces complexity in the form of adversarial assaults, model interpretability, and data privacy issues. For users to trust AI-driven security systems and to comprehend their decision-making processes, openness of these systems is essential.
- 2 February 2024
- Published by IGI Global Scientific Publishing
- p. 34-58
Impact of Artificial Intelligence and Machine Learning in Cloud Security
The rapid advancement of artificial intelligence (AI) and machine learning (ML) technologies has had a significant impact on cloud security, as it has in many other sectors. This abstract examines how AI and ML are affecting cloud security, highlighting their major contributions, difficulties, and potential. Traditional approaches to cloud security provide improved threat detection, real-time monitoring, and adaptive defense mechanisms. These technologies are adept at processing enormous volumes of data, allowing them to spot trends, anomalies, and potential dangers that more traditional security measures would miss. In order to quickly identify and take appropriate action in response to unauthorised access, data breaches, and other malicious activities, AI-driven systems can quickly analyse user behaviour, network behaviour, and system logs. It introduces complexity in the form of adversarial assaults, model interpretability, and data privacy issues. For users to trust AI-driven security systems and to comprehend their decision-making processes, openness of these systems is essential.