Skip to content
View LeoMartinezTAMUK's full-sized avatar
🎯
Focusing
🎯
Focusing
2 followers · 1 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report LeoMartinezTAMUK

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
LeoMartinezTAMUK/README.md

leomartineztamuk

Hi, I'm Leo👋

AI/LLM Security Engineer focused on cybersecurity, LLM evaluation, and AI-driven detection systems

About Me

I'm a former Computer Science graduate with experience across AI security, cybersecurity, software engineering, and applied machine learning. My work focuses on evaluating and building AI systems in security-focused environments, especially around LLM behavior, adversarial testing, vulnerability discovery, and cyber reasoning.

Currently, I work on AI/LLM security evaluations, where I assess model behavior against jailbreaks, prompt injection, unsafe cyber outputs, sensitive information disclosure, and reasoning failures.

Technical Toolkit

Languages: Python, Java, C++, JavaScript, SQL, Bash

AI/ML: LLMs, RAG, LangChain, Vector Databases, Keras, Scikit-learn

Cybersecurity: AI Security, LLM Evaluation, Red Teaming, MITRE ATT&CK, Threat Intelligence

Tools: Git, Docker/Podman, AWS, Azure, Splunk, Wireshark, Burp Suite, Kali Linux

Contact

Feel free to connect with me on LinkedIn or reach me at mtz3.leo@gmail.com.

Pinned Loading

  1. Network_Intrusion_DNN-CTGAN Network_Intrusion_DNN-CTGAN Public

    Utilizing Generative AI coupled with Deep Neural Networks to classify network intrusions from the widely recognized NSL-KDD dataset and is based on a research paper I produced in Spring 2024 with t…

    Jupyter Notebook 4

  2. mcp-strike mcp-strike Public

    Active adversarial security scanner for Model Context Protocol (MCP) servers: runtime attacks, LLM-as-judge, and an adaptive agent.

    Python

  3. Home-Lab-SOC-Portfolio Home-Lab-SOC-Portfolio Public

    A simulated Security Operations Center (SOC) lab built with VirtualBox. This repository documents full kill-chain cyber attacks, Suricata NIDS detection validation, and a custom Python-based SOAR i…

    Python

  4. codebase_AI-agent codebase_AI-agent Public

    This project implements a minimal and deterministic AI agent that can search, analyze, and build a large C++ codebase under a strict 5,000‑token budget.

    Python

  5. ML-Based_MTD ML-Based_MTD Public

    M.T.D. is a project that tackles the growing risks faced by industries worldwide due to cyber threats. Our project employs a comprehensive approach to address various cyber-attacks, focusing on int…

    Python 2

  6. CNN-CTGAN_5-Class_ID CNN-CTGAN_5-Class_ID Public

    Combining a Convolutional Neural Network (CNN) and Conditional Tabular Generative Adversarial Networks (CTGAN) to perform multi-class classification for Network Intrusion Detection.

    Python 2 1