AI Security & Red Teaming: Master direct/indirect attacks, RAG poisoning, AI agent risks, and defense-in-depth.
What You Will Learn:
Execute Direct and Indirect Prompt Injection attacks to expose vulnerabilities in LLMs, RAG pipelines, and autonomous AI Agents.
Design a robust "Defense-in-Depth" architecture to protect AI applications from malicious inputs, data exfiltration, and unauthorized actions.
Automate AI Red Teaming and security testing using industry-standard tools like Promptfoo, Garak (NVIDIA), and PyRIT (Microsoft).
Harden system prompts and implement input/output validation to effectively mitigate the #1 vulnerability on the OWASP LLM Top 10.
Identify and exploit advanced AI attack vectors, including RAG knowledge base poisoning, multimodal image injection, and invisible text steganography.
Analyze real-world AI security failures (like the GitHub Copilot RCE and Bing Chat leaks) to understand attacker mindsets and prevent costly breaches.
