OWASP ML Security Top 10
A walkthrough for OWASP Top 10 for Machine Learning Security. Practical insights about the ML document
Securing RAG: A Pentester's Approach
As AI continues to evolve, Retrieval-Augmented Generation (RAG) has emerged as a transformative approach, combining language models with external knowledge sources to produce precise, real-time content. However, this innovation introduces new risks: RAG systems create a unique attack surface that must be carefully addressed.
In this session, I will explain how RAG works and guide you through a series of critical vulnerabilities, including data poisoning, prompt injection, and unauthorized data exposure. Through live demos, I will demonstrate how attackers can exploit these vulnerabilities, with real-world examples showing why securing RAG-based models is crucial.
We will go beyond identifying the risks—I'll share practical defense strategies and best practices to protect your RAG systems. By the end of the session, you'll be equipped with the knowledge and tools needed to secure your AI applications, ensuring they remain safe and reliable.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top