Portfolio
12 focused projects showcasing my security research — from Byzantine-robust federated learning to malware analysis and published cryptographic methods
An enterprise portfolio of 10 production-ready AI systems, demonstrating scalable RAG applications, LangGraph security agents, and robust LLMOps deployment.
A secure federated learning framework that lets US states collaboratively train healthcare fraud detection models without sharing sensitive patient data.
A comprehensive 21-project portfolio demonstrating advanced privacy-preserving machine learning applied to phishing detection, including Homomorphic Encryption, TEEs, and Zero-Knowledge Proofs.
A massive 30-project research portfolio exploring federated learning security, featuring the novel SignGuard multi-layer defense system to protect decentralized AI from adversarial attacks.
A static analysis engine with 95.7% accuracy that reverse-engineers and classifies zero-day banking trojans by extracting behavioral fingerprints.
An advanced deep learning forecasting engine that predicts Indonesia's critical economic indicators—like inflation and exchange rates—using an ensemble of neural networks.
Quantitative trading system for IDX stocks combining LSTM/SVR ensembles with technical analysis strategies, featuring walk-forward validation and risk management.
A production machine learning system that analyzes 227 million Medicaid records to automatically detect and flag complex healthcare fraud.
An interactive dashboard that makes $1.09 Trillion in healthcare spending transparent, allowing investigators to visually explore ML-flagged fraud anomalies.
This high-performance, statically generated portfolio website you are looking at right now, built from scratch with Astro, React, and Tailwind CSS.
Novel multi-layer defense system combining ECDSA digital signatures, multi-factor anomaly detection, and time-decay reputation scoring to protect federated learning from Byzantine poisoning attacks.
My published peer-reviewed research natively hiding data within images using advanced cryptographic encodings to mathematically defeat detection tools.