Research

Developed an artificial neural network-driven volatility arbitrage strategy using LSTMs to forecast short-term deviations between realized and implied volatility.

Developing novel approaches to bypass Pointer Authentication Codes in iOS kernel exploitation. Research focuses on understanding modern iOS security mechanisms and developing practical exploitation techniques.

Machine learning approaches to forecasting volatility surfaces in options markets. Exploring deep learning architectures for modeling complex volatility dynamics across strikes and maturities.

High-frequency analysis of orderbook dynamics and price discovery mechanisms. Investigating how information propagates through market microstructure and its implications for trading strategies.