I am a PhD candidate in Information Science and Engineering at the Nara Institute of Science and Technology, Japan, with a strong focus on financial cybersecurity, adversarial machine learning, and federated learning (FL). My research spans data security, secure AI systems, computer vision, and model explainability, with real-world applications in credit card fraud detection, malware detection, and secure financial transactions.Currently, I am working on adversarial attacks and defenses for federated learning models, particularly in the financial sector, and exploring federated transfer learning (FTL) for robust model security. I have also contributed to healthcare-related research, with my master's work focusing on MRI-based brain tumor classification using deep learning.In addition to academic research, I have experience in teaching and curriculum development in computer science, cybersecurity, and digital logic design, with a commitment to preparing the next generation of cybersecurity experts.I have collaborated with leading institutions such as the University of Texas at Dallas, the University of Tokyo, and The University of Queensland. I am passionate about advancing the security, interpretability, and adaptability of AI systems across multiple domains, including finance, healthcare, and IoT.Research Interests:Financial CybersecurityFederated Learning (FL)Adversarial AI & Model RobustnessComputer VisionExplainable AIMulti-modal AI SystemsHighlights:Published research on secure federated learning models for credit card fraud detection and banking malware detection.Experience in international collaborations with institutions in the USA, Japan, and Australia.Extensive teaching experience in computer science.Long-term Goals: To advance AI security and interpretability in federated learning and multi-modal data integration, ensuring trustworthiness across diverse industries such as finance and healthcare.