Research
Benchmarking LLM-Generated Code Security via Static Analysis and CWE Scanning
Aug 2025 - Present
Investigating how LLMs introduce security vulnerabilities into AI-generated code. The study benchmarks insecure coding patterns across programming languages, IDEs, and prompt types using static analysis tools such as Semgrep, CodeQL, and Bandit, mapped to CWE/CVSS/OWASP standards.
Using Transformers and DL with Stance Detection to Forecast Crypto Price Movement
May 2022 - Dec 2022
Developed a stance-detection-based forecasting system that predicted Bitcoin price movements by combining transformer-based NLP and deep learning time-series models. Achieved 80% stance-detection accuracy and a mean absolute error of $1,144 on price prediction.