Samir Poudel
I build distributed AI systems that preserve privacy. My research spans federated learning, blockchain security, and robust machine learning.
About Me
Research background and interests
I'm a Ph.D. candidate in Computational and Data Science at Middle Tennessee State University, with a background in Software Engineering.
My research builds privacy-preserving distributed AI systems that span federated learning, blockchain security, and robust machine learning.
Research Interests
Education
Contact
Publications
0 peer-reviewed publications · 0 total citations
Experience, Skills & Talks
3+ years research at MTSU · 10+ international conferences · Full-stack & ML expertise
Projects
Selected research and engineering projects
Academic Tracker
Full-stack grade tracker with AI syllabus extraction, live grade calculator, and animated progress visualization per course.
I-140 Insights
Tracks USCIS I-140 immigration cases across all service centers by enumerating receipt numbers, with automated scraping and analytics dashboard.
Edge-Case Backdoor Detection (RBBD)
Representation-based defense framework for federated learning, reducing attack success rates below 15%.
Privacy-Preserving Environmental Monitoring
Federated learning framework using satellite imagery for deforestation detection, achieving 0.85 IoU.
Cloud Fake News Detection
Serverless AWS solution (BERT/LSTM) with 94.9% accuracy and low latency.
Credit Card Fraud Detection
PySpark/Airflow batch system achieving 94.9% accuracy with imbalanced data.
Research Figures
Architectures and visualizations from published work
Federated Learning Architecture
Fake News Detection System
GAN Educational Architecture
QuadraCode AI
IoT Framework
UNETeM Architecture
Get In Touch
Want to discuss research or ask about my work?
Drop me an email, connect on GitHub, or check my Google Scholar profile.