This project focused on building and testing a practical AI security assessment lab for evaluating LLM defenses against prompt injection and jailbreak attacks.

I integrated Spikee by Reversec with a locally hosted cybersecurity model running through LM Studio, then added NVIDIA NeMo Guardrails to compare model behavior under three conditions: no guardrails, input filtering, and combined input/output protection.

The work included configuring the local model environment, building a custom FastAPI gateway, integrating NeMo Guardrails, troubleshooting model latency and timeout issues, creating a reusable Spikee target, and analyzing attack results using Spikee’s built-in reporting tools.

The project also explored different adversarial testing approaches, including prompt injection datasets, obfuscation, encoded attacks, Best-of-N testing, synthetic canary leakage tests, and structured benchmark comparisons.

The objective was to measure how much the guardrails reduced successful attacks while keeping the model, dataset, and testing conditions consistent.

Tools used: Spikee, NVIDIA NeMo Guardrails, LM Studio, Python, FastAPI, PowerShell, Parrot OS, local LLMs, JSONL datasets, and custom security testing scripts.

This project demonstrates a hands-on approach to LLM red teaming, AI safety testing, prompt-injection assessment, and guardrail validation for organizations deploying generative AI systems.

pretty cool tbh. testing the same attacks with different guardrail setups makes the results way more interesting.

𝐅𝐮𝐥𝐥 𝐒𝐭𝐚𝐜𝐤 𝐀𝐈 𝐋𝐞𝐚𝐫𝐧𝐢𝐧𝐠 𝐌𝐚𝐧𝐚𝐠𝐞𝐦𝐞𝐧𝐭 𝐒𝐲𝐬𝐭𝐞𝐦

𝐌𝐲 𝐫𝐨𝐥𝐞: Lead Full Stack Developer (AI & LMS Platform)

𝐏𝐫𝐨𝐣𝐞𝐜𝐭 𝐝𝐞𝐬𝐜𝐫𝐢𝐩𝐭𝐢𝐨𝐧: I led the development of a scalable AI-powered learning platform and LMS portal. I built a secure full-stack architecture with responsive frontend interfaces and robust backend APIs to support interactive lessons, real-time class scheduling, and personalized learning tools. I also integrated curriculum-based workflows and ensured the system performed reliably for thousands of active students.