Research
Operating at the intersection of artificial intelligence and cybersecurity.
// cat research_areas.md
[01]
Autonomous Offensive Security
RL-trained agents that discover and exploit vulnerabilities end-to-end—characterizing the frontier of AI cyber capabilities, building the benchmarks to measure them, and translating findings into actionable defense.
[02]
AI Cyber Capability Evaluation
Designing realistic environments, experiments, and metrics that elicit and measure what AI systems can actually do in security contexts—from CTF-scale challenges to full-lifecycle attack simulations against defended infrastructure.
[03]
AI Safety for Adversarial Domains
Understanding how autonomous agents behave under adversarial pressure—emergent misalignment from reward hacking, capability elicitation methodology, containment architecture, and the policy implications of AI systems reaching expert-level cyber capabilities.
// active focus
>
cat current_work.txt
Building autonomous pentesting systems. Designing and shipping AI agents that execute the full attack chain end-to-end—automated reconnaissance, vulnerability discovery, exploit development, and remediation—without human intervention.
// cat talks.log
>
grep -r "recent" talks/
NYU OSIRIS Lab — "Autonomous Offensive Security"
BSides Connecticut — "AI-Powered Spear Phishing: Precision Attacks at Machine Speed"
Columbia University — "The Evolution of AI-Powered Cyberattacks: How APTs and Cybercrime Groups are Leveraging AI"
// cat teaching.log
>
cat ~/teaching/current_semester
Fordham University — Data Structures (C++)