RESEARCH

Research at the intersection
of AI and cybersecurity.

My research examines the security, reliability, fairness, and robustness of AI systems, with a particular focus on biometric security and machine-learning-enabled cybersecurity.

01

Fairness-Aware Face Presentation Attack Detection

My initial research investigated demographic disparities in Face Presentation Attack Detection systems and explored methods for reducing performance differences between demographic groups.

Explore this research →
02

Architectural Bias in Face PAD

The second phase examined whether the choice of neural architecture itself can contribute to demographic differences in Face Presentation Attack Detection.

Explore this research →
03

Fairness Under Distribution Shift

The third phase asks whether fairness observations remain reliable when models are evaluated across datasets and repeated across random seeds.

Explore this research →
04

Current AI Security Research

My current research includes Microsoft-funded work involving malware analysis and the evaluation of security systems against evolving threats.