Course · 5 chapters
Adversariale KI
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: Hier starten
Eine Orientierung über den vierteiligen Adversarial AI Skill Path – Verteidiger → Angriffsfläche → Offensive → Programm – von deinem ersten Prompt-Injection-Patch bis zum Betrieb einer internen Red-Team-Praxis, die 2026er-Angriffen standhält.
- 2Grundlagen der Prompt-Injection-Abwehr
Warum Prompt Injection existiert, wie Angreifer sie ausnutzen und welche mehrschichtige Verteidigung jedes LLM-Feature vor dem Launch braucht.
- 3Context Poisoning & Indirect Injection
Kartiere und verteidige die Angriffsfläche der Agent-Ära — RAG-Poisoning, dokumentbasierte Payloads, Memory-Poisoning und Tool-Output-Hijacking, die von Direct-Injection-Abwehr nicht erfasst werden.
- 4Automatisiertes Jailbreak-Tooling
Angreifer-LRMs, BYO-Attacker-Muster, das DeepTeam / PyRIT / Mindgard-Trio und die automatisierten Algorithmen (PAIR, TAP, GCG), die Red-Teaming von einer Einzelperson-Aufgabe in ein kontinuierliches Programm verwandeln.
- 5AI Red Teaming & Adversarial Evaluation
Ein Red-Team-Programm fuer Produktions-KI aufsetzen — Taxonomie, der Finding-Lifecycle, Runtime-Monitoring, Regressionsdisziplin und das interne Playbook.
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.