Finished up training with Brian and Derek on Red Teaming AI. Since everyone is shoving LLMs into their products, I wanted to understand the attack surface. We went through the OWASP LLM Top 10 in detail. I got hands on experience with prompt injection attacks, bypassing safety filters, and understanding how data poisoning works. We also covered ways to defend against these attacks and how to properly sandbox AI plugins. This is definitely a skillset I plan on expanding.
View the official training page here
View my official credential here