Projects
Real-time Windows EDR System
January 2024 - Present
- Architected a real-time Windows Endpoint Detection and Response system with C/C++ kernel-mode drivers for low-latency system call interception.
- Designed and benchmarked 7+ prevention algorithms, reducing false positive rates to less than 1.0% while maintaining robust prevention capabilities.
- Engineered a parallelized analysis pipeline for 60M+ kernel trace events using hierarchical structures and anomaly detection.
- Developed automated evaluation infrastructure across 6,000+ malware and benign samples for prevention metrics including TPR, FPR, and precision.
- Built proactive access-control generation techniques that prevent malware execution by enforcing blocking rules before runtime execution.
EchoCrypt: High-Performance Side-Channel Analysis Framework
August 2024 - March 2025
- Developed a modular acoustic side-channel attack framework integrating Vision Transformers, Swin Transformers, and large language models for keystroke recovery in noisy environments.
- Optimized inference and evaluation pipelines to achieve 90%+ recovery accuracy across unconstrained recordings.
- Implemented LoRA fine-tuning for LLaMA models, reducing memory requirements by approximately 90% while retaining strong contextual correction performance.
- Built reproducible PyTorch and CUDA data augmentation and benchmarking pipelines across diverse Zoom and phone audio datasets.
Interactive Malware Feature Engineering Lab
October 2024 - November 2025
- Architected and deployed a containerized web application with Docker, Nginx, and Gunicorn for real-time malware feature experimentation.
- Engineered a Django backend for budget-constrained Random Forest training jobs over 33+ static PE features.
- Designed an interactive interface that provides real-time feature-importance feedback and makes malware analysis workflows more accessible.
- Configured production deployment components to support concurrent user sessions and iterative model training.