Course · 5 chapters
Adversarial AI
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.
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
- 1Adversarial AI: parti da qui
Un orientamento sullo percorso Adversarial AI in quattro capitoli — difensore → superficie di minaccia → offesa → programma — che copre tutto, dalla tua prima patch contro la prompt injection alla gestione di una pratica interna di red-team che regge gli attacchi del 2026.
- 2Fondamenti di difesa dalla prompt injection
Perché la prompt injection esiste, come gli attaccanti la sfruttano e la difesa a strati di cui ogni funzione basata su LLM ha bisogno prima del rilascio.
- 3Context Poisoning e Indirect Injection
Mappa e difendi la superficie d'attacco dell'era degli agenti — poisoning del RAG, payload veicolati dai documenti, poisoning della memoria e dirottamento dell'output dei tool che le difese contro l'injection diretta non raggiungono.
- 4Strumenti automatici di jailbreak
LRM attaccanti, pattern BYO-attacker, il trio DeepTeam / PyRIT / Mindgard e gli algoritmi automatici (PAIR, TAP, GCG) che trasformano il red-teaming da attività di un singolo ingegnere a un programma continuo.
- 5Red teaming AI e valutazione avversariale
Mandare avanti un programma di red-team per l'AI in produzione — tassonomia, ciclo di vita dei finding, monitoraggio runtime, disciplina di regression e il playbook interno.
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.