Saltar al contenido

cat about.md

About

Soy AI Security Researcher @ Straiker y Red Team Operator, desde México. Aquí reúno algunos de mis writeups, blogs y cosas que he hecho. Me gusta romper la IA, las operaciones de red team y la investigación.

whoami ACTIVE
handle
briancgx
role
AI Security Researcher @ Straiker
also
Red Team Operator
team
Straiker
location
México
contact
contact@briancgx.me

offensive stack

  • Red teaming
  • Web / infra exploitation
  • Pivoting & tunneling
  • Privilege escalation

ai security stack

  • LLM red teaming
  • Prompt injection
  • Agentic tool-use abuse
  • AI security research

# certifications

  • C-AgAIPen badge

    C-AgAIPen

    Certified Agentic AI Pentester

    The SecOps Group · 2026

  • CPTS badge

    CPTS

    Certified Penetration Testing Specialist

    Hack The Box · 2026

  • BSCP badge

    BSCP

    Burp Suite Certified Practitioner

    PortSwigger · 2025

  • C-AI/MLPen badge

    C-AI/MLPen

    Certified AI/ML Pentester

    The SecOps Group · 2025

  • CRTeamer badge

    CRTeamer

    Certified Red Teamer

    The SecOps Group · 2025

  • eWPTX badge

    eWPTX

    Web Application Penetration Tester eXtreme

    INE Security · 2025

HTB Pro Labs · Red Team Operator L1: Dante FullHouse POO

# publications

  • ICCBR 2024 · XCBR Workshop (CEUR-WS Vol-3708)2024
    Counterfactual Explanation of a Classification Model for Detecting SQL Injection Attacks

    Proposes a machine-learning classifier to detect SQL injection attacks and makes it interpretable through counterfactual explanations (XAI) — surfacing the minimal changes to a query that would flip the model’s decision. It brings explainable AI to database security so analysts can understand and trust alerts instead of treating them as a black box.

    • XAI
    • Counterfactuals
    • SQL Injection
    • Machine Learning
  • JAICA · Vol. 2 (2)2024
    A Deep Learning Approach for Automated Identification of Triatoma infestans Using YOLOv8

    Applies computer vision with YOLOv8 to automatically identify Triatoma infestans, the main vector of Chagas disease, training on 91 labeled images and 9,100 augmented ones. It reaches a mAP@50 of 0.9588 and tells the vector apart from similar insects with no false positives, laying the groundwork for entomological surveillance on mobile and embedded systems.

    • YOLOv8
    • Computer Vision
    • Chagas
    • Vector Surveillance