Join this compelling presentation to uncover the hidden dangers and challenges of AI security in modern use cases. The focus is on analyzing Retrieval Aided Generation (RAG) applications and the associated security risks. Learn how inadequate data permissions in vector databases can lead to unauthorized access and data breaches.

Another exciting focus is the threat of prompt injection. This attack method, where malicious inputs are embedded into the prompt, reveals how severe security vulnerabilities can arise even in non-chatbot scenarios. The presentation highlights how attackers can exploit these weaknesses to trigger unwanted actions or compromise sensitive data.

This presentation offers a comprehensive analysis of current threats and challenges in AI secu ...