Master’s Thesis Defense, The University of Texas at El Paso, El Paso, Texas, United States
Presented as a Master’s thesis defense for the M.S. in Computer Science. This presentation examined generalizable learning systems for dynamic cybersecurity environments using meta-learning and reinforcement learning, with applications to malware detection and network security simulation.
Education Session, Association for Assessment and Research in Counseling (AARC), Daytona Beach, Florida, United States
A 50-minute education session introducing core artificial intelligence and machine learning concepts for counselor educators and researchers, based on our published paper “Understanding Artificial Intelligence and Machine Learning: Foundational Concepts for Counselor Education”
Poster, IPS-AI Course Showcase, University of Texas at El Paso, El Paso, Texas, United States
Presented a poster exploring how machine learning can predict chronic health outcomes using Adverse Childhood Experiences (ACEs) data. The study used the 2023 BRFSS dataset and applied models such as Logistic Regression, Random Forest, and SVM to uncover links between ACEs and long-term health risks.
Poster, Graduate Expo 2025, University of Texas at El Paso, El Paso, Texas, United States
Presented a poster on using meta-learning techniques to improve malware detection across unseen malware families. The project integrates Model-Agnostic Meta-Learning (MAML) with datasets like BODMAS, MaleVis, and Avast-CTU to enhance model generalization in cybersecurity contexts.
Presentation, BigCyber-2024 Workshop, IEEE International Conference on Big Data (BigData), Hybrid (Recorded Presentation)
Recorded presentation of our accepted paper at the BigCyber-2024 Workshop, part of the 2024 IEEE International Conference on Big Data.
The talk highlights our use of meta-learning (MAML) to develop models that generalize across unseen malware families using diverse datasets such as BODMAS, Avast-CTU, and MaleVis.