Course · 5 chapters

IA Adversarial

Ship LLM features that survive attack. Defend against prompt injection, context poisoning, and jailbreaks, then run an internal red-team program. 5 chapters, advanced, for engineers.

Paidadvanced5 chapters100 minEnglish + 6 languagesCertificate on completion

What you'll be able to do

  • Defend LLM features against prompt injection
  • Harden AI agents against data poisoning
  • Automate jailbreak testing with DeepTeam
  • Run proven attack algorithms like PAIR
  • Turn attack discovery into cheap CI gates
  • Run an internal AI red-team program

What's inside

  1. 1
    Adversarial AI: Empieza Aquí

    Una orientación por las cuatro etapas del skill path de Adversarial AI — defensor → superficie de amenazas → ofensiva → programa — cubriendo todo desde tu primer parche de prompt injection hasta ejecutar una práctica interna de red team que sobreviva los ataques de 2026.

    12 min
  2. 2
    Fundamentos de defensa contra prompt injection

    Por qué existe el prompt injection, cómo lo explotan los atacantes, y la defensa en capas que toda funcionalidad con LLM necesita antes de salir a producción.

    22 min
  3. 3
    Envenenamiento de contexto e inyección indirecta

    Mapea y defiende la superficie de ataque de la era de los agentes — envenenamiento de RAG, cargas útiles en documentos, envenenamiento de memoria y secuestro de salidas de herramientas que las defensas contra inyección directa no alcanzan.

    22 min
  4. 4
    Herramientas de Jailbreak Automatizado

    LRMs atacantes, patrones de atacante propio (BYO-attacker), el trío DeepTeam / PyRIT / Mindgard y los algoritmos automatizados (PAIR, TAP, GCG) que convierten el red-teaming de una tarea de un solo ingeniero en un programa continuo.

    22 min
  5. 5
    Red teaming de IA y evaluación adversarial

    Ejecuta un programa de red team para IA en producción: taxonomía, ciclo de vida de hallazgos, monitoreo en tiempo real, disciplina de regresión y el playbook interno.

    22 min

Frequently asked questions

What will I learn in this adversarial AI course?
You learn to defend and attack LLM-powered systems: patching prompt injection with defense-in-depth, blocking context poisoning and indirect injection across RAG and agents, running automated jailbreak tooling, and operating an internal AI red-team program. The path spans five chapters across the defender, threat-surface, offense, and program stages.
Who is this AI security path for?
It is built for engineers shipping production LLM features and the security teams that test them. The level is advanced, so it assumes you already work with LLM apps, agents, or RAG pipelines.
Do I need coding experience or prior AI security knowledge?
Yes. This is an advanced engineering path, so you should be comfortable building LLM features and reading code. It uses offensive tools like PyRIT, DeepTeam, and Mindgard, so familiarity with running Python tooling helps.
How long does the Adversarial AI course take and is there a certificate?
The path runs about 100 minutes across five chapters, including a short orientation chapter. You earn a completion certificate once you finish every chapter.
Is this course free?
No. Adversarial AI is a paid path included with AI Academy by Anthropos. It covers prompt injection defense, context poisoning, automated jailbreak tooling, and AI red teaming.

Earn a certificate

Complete all chapters to receive your certificate of completion.