NCyTE

How to move beyond static regex filters by using Open Policy Agent (OPA) and Rego to enforce declarative, explainable security policies on AI prompts.

How to decouple AI defense from the model by building a Python Flask security proxy with hot-reloading ingress filters and egress data masking.

How to probe and break local LLMs using Direct Injection, Roleplay, Obfuscation, and Authority Claims, demonstrating why system instructions fail as security boundaries.

How to build a 100% free, local AI security sandbox using Docker Desktop, Ollama (llama3.2), and a custom vulnerable chatbot to test prompt injection defenses without cloud API costs.

As the father of a college student with autism, my approach to inclusive teaching is both professionally grounded and deeply personal. I see firsthand how traditional, single-mode instructional methods can create unintentional barriers for neurodivergent learners or students balancing non-traditional paths. To foster an environment where every student can succeed regardless of their starting point or learning style, I focus on building multimodal, accessible, and low-cost learning environments across three key areas. ...

In August 2026 I delivered a webinar for the NCyTE Center on a question I kept hearing from community college faculty: how do you teach AI security when you don’t have a budget, your IT department locks down what you can install, and API costs for a live LLM are unpredictable? The answer I built — and the one this post walks through — is a zero-cost, fully local lab that any instructor can drop into their course next week. ...