Aulafy
ESEN
Courses
Home/Courses/AI security and evaluation
capsule/seguridad-evals

AI security and evaluation

A practical security path for prompts, agents and models: evals, red teaming, data risks, guardrails and responsible deployment.

Intermediate 7 lessons Free and open source
Start lessons

Lessons are available in English. Code snippets keep original commands and file names intact.

modules
3
lessons
7
status
open
Roadmap

Syllabus

7 steps

module 01 / Risk and mental model

2 lessons
  1. 1Generative AI Risk Map/seguridad-evals/mapa-riesgos
  2. 2OWASP Top 10 for LLMs Explained/seguridad-evals/owasp-llm

module 02 / Measure before trusting

2 lessons
  1. 3Basic evals and regressions/seguridad-evals/evals-basicas
  2. 4Red teaming and jailbreaks/seguridad-evals/red-teaming

module 03 / Responsible production

3 lessons
  1. 5Privacy, Logs, and Sensitive Data/seguridad-evals/privacidad-datos
  2. 6Model and dataset supply chain/seguridad-evals/supply-chain
  3. 7Project: AI App Audit/seguridad-evals/proyecto-auditoria
View all courses