Victor Stany Rozario
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Victor Stany Rozario has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Dip Nandi
Department of Computer Science, American International University-Bangladesh (AIUB), Dhaka, Bangladesh
2 shared publications - Azm Ehtesham Chowdhury
Dept. of CS FSIT American International University-Bangladesh (AIUB). Dhaka Bangladesh
1 shared publication - Dipta Gomes
American International University-Bangladesh, Bangladesh
1 shared publication Ehtesham Azm
Dept. of CS FSIT American International University-Bangladesh (AIUB). Dhaka Bangladesh
1 shared publication- Farzana Fariha
American International University
1 shared publication Jahan Morshed
Dept. of CS FSIT American International University-Bangladesh (AIUB). Dhaka Bangladesh
1 shared publication
Latest Publications
- 1 May 2026
- Published by IGI Global Scientific Publishing
Technological Advances in Generative and Explainable AI for Next-Generation Cyber Defense
This manuscript surveys the transformative convergence of Generative AI (GenAI) and Explainable AI (XAI) in cybersecurity, addressing computational democratization and evolving threats like polymorphic malware 2.0, LLM-chaining, deepfakes, and adversarial poisoning. Through systematic review of 2022-2025 literature, it analyzes GenAI applications in SOCs such as dynamic playbooks, LLM threat hunting, GAN synthetic data—and critiques XAI limitations (e.g., SHAP latency), proposing neuro-symbolic hybrids and federated frameworks. Hardware innovations like AI-driven Trojan detection and PUFs are evaluated alongside taxonomies for unified paradigms. Findings reveal enhanced detection accuracy and interpretability, yet gaps in real-time scalability persist. Future directions emphasize causal reasoning, adversarial robustness, and regulatory compliance for trustworthy cyber defense.
- 1 May 2026
- Published by IGI Global Scientific Publishing
Technological Advances in Generative and Explainable AI for Next-Generation Cyber Defense
This manuscript surveys the transformative convergence of Generative AI (GenAI) and Explainable AI (XAI) in cybersecurity, addressing computational democratization and evolving threats like polymorphic malware 2.0, LLM-chaining, deepfakes, and adversarial poisoning. Through systematic review of 2022-2025 literature, it analyzes GenAI applications in SOCs such as dynamic playbooks, LLM threat hunting, GAN synthetic data—and critiques XAI limitations (e.g., SHAP latency), proposing neuro-symbolic hybrids and federated frameworks. Hardware innovations like AI-driven Trojan detection and PUFs are evaluated alongside taxonomies for unified paradigms. Findings reveal enhanced detection accuracy and interpretability, yet gaps in real-time scalability persist. Future directions emphasize causal reasoning, adversarial robustness, and regulatory compliance for trustworthy cyber defense.
- 17 October 2024
- Published by Springer Nature
- p. 511-526
Geo-temporal Disease Visualization of Bangladesh from Empirical Data Using Machine Learning
- 17 October 2024
- Published by Springer Nature
- p. 511-526
Geo-temporal Disease Visualization of Bangladesh from Empirical Data Using Machine Learning
- Open Access
- 8 October 2024
- Published by E-palli in American Journal of Interdisciplinary Research and Innovation
- p. 40-46
A Comprehensive Analysis on Non-Communicable Diseases by Quantitative Approach: Using Graphical Visualization
Non-communicable diseases (NCDs) have already become major killers in Bangladesh. Once NCDs are developed, they become chronic health and economic problems. Their primary prevention is linked to their common risk factors. This study was conducted to visualize the trend of the diseases along with the age factor in rural areas of Bangladesh. A quantitative method was used throughout the research to reach the desired goal of this study. The data was collected from a medical association to use in this research and for processing the graphical visualization some preprocessing techniques are also applied on the raw data. After completing the research, the researchers found the percentage of the patients according to the diseases and the disease count along with the patients’ age. The outcome is totally represented in graphical visualization. This research will help to find the numeric measurement of a particular disease considering age factor which can help to reduce the issues in medical sectors.
- 8 October 2024
- Published by E-palli in American Journal of Interdisciplinary Research and Innovation
- p. 40-46
Open AccessA Comprehensive Analysis on Non-Communicable Diseases by Quantitative Approach: Using Graphical Visualization
Non-communicable diseases (NCDs) have already become major killers in Bangladesh. Once NCDs are developed, they become chronic health and economic problems. Their primary prevention is linked to their common risk factors. This study was conducted to visualize the trend of the diseases along with the age factor in rural areas of Bangladesh. A quantitative method was used throughout the research to reach the desired goal of this study. The data was collected from a medical association to use in this research and for processing the graphical visualization some preprocessing techniques are also applied on the raw data. After completing the research, the researchers found the percentage of the patients according to the diseases and the disease count along with the patients’ age. The outcome is totally represented in graphical visualization. This research will help to find the numeric measurement of a particular disease considering age factor which can help to reduce the issues in medical sectors.
- 14 August 2024
- Published by Springer Nature
- p. 167-187
Enhancing Breast Cancer Detection Systems: Augmenting Mammogram Images Using Generative Adversarial Networks
- 14 August 2024
- Published by Springer Nature
- p. 167-187
Enhancing Breast Cancer Detection Systems: Augmenting Mammogram Images Using Generative Adversarial Networks
- Open Access
Community Detection in Social Network using Temporal Data
Social networks facilitate the social space where actors or the users have ties among them. The ties and their patterns are based on their life styles and communication. Similarly, in online social media networks like Facebook, Twitter, Myspace etc., multiple users belong to multiple specific communities. The social network represents large real-world directed social graphs. Detection of communities or clusters from these graphs is a problem of considerable research interest. The communities are formed using the neighboring nodes that have common edges and common attributes. Most of the existing community detection algorithms usually consider node contents to analyze the attributes of community. Some algorithms use the links between the nodes to determine the dense regions in the graph. But utilizing both the edge content and the vertex content to detect community are yet to be considered and verified, since the traditional extraction methods of vertex and edge data do not consider the connectivity among the nodes. This paper presents an Interlinked Spatial Clustering Model (ILSCM) which provides relevant content selection and extraction of the temporal topics for identifying the betweenness among the nodes based on the context keys to detect community.
Open AccessCommunity Detection in Social Network using Temporal Data
Social networks facilitate the social space where actors or the users have ties among them. The ties and their patterns are based on their life styles and communication. Similarly, in online social media networks like Facebook, Twitter, Myspace etc., multiple users belong to multiple specific communities. The social network represents large real-world directed social graphs. Detection of communities or clusters from these graphs is a problem of considerable research interest. The communities are formed using the neighboring nodes that have common edges and common attributes. Most of the existing community detection algorithms usually consider node contents to analyze the attributes of community. Some algorithms use the links between the nodes to determine the dense regions in the graph. But utilizing both the edge content and the vertex content to detect community are yet to be considered and verified, since the traditional extraction methods of vertex and edge data do not consider the connectivity among the nodes. This paper presents an Interlinked Spatial Clustering Model (ILSCM) which provides relevant content selection and extraction of the temporal topics for identifying the betweenness among the nodes based on the context keys to detect community.