Cloud security × AI-assurance research. I build research software that exposes what an AI-assurance claim establishes, what it assumes, and where it must stop.
Penn State CS ’26 (Cybersecurity minor), AWS CCP + AI Practitioner. My research question: what do composed AI guardrails actually guarantee when their joint behavior was never measured? My flagship, CC-Framework, answers with Fréchet–Hoeffding bounds and claim governance — see the five-minute case study. At Penn State's S2 Lab I build Ghost-Ark, a verifier for the provenance limits of AI-governance receipts. Every claim on my site carries its evidence or says it can't — the evidence ledger has the bindings.
Supervised by Dr. Peng Liu. Reinforcement, interference, and dependence-driven failure in composed LLM safety systems using probabilistic bounds and copula-family reasoning. CC-Framework is the primary deliverable, with theorem notes, research memos, and architecture documentation.
Python CNF-conversion tooling for SAT-solving and logical-verification workflows; evaluation of LLM-assisted formalization of natural-language logic — translation reliability, ambiguity handling, verification-readiness.
Coursework: computer security, operating systems, data structures, algorithms, statistical inference, theory of computation.
SAA-C03 and Security — Specialty in progress. Verification IDs available on request.
Phone number deliberately omitted from the open web — email me and I’ll send the full PDF résumé. Biographical claims on this page are owner-attested; see the evidence ledger for what that means here.