Hidden Risks of Integrating AI: Extracting Private Data with Real-World Exploits - 17 de febrero de 2026 - TecnoWebinars.com

This webinar explores the hidden risks in apps leveraging modern AI systems, especially those using large language models (LLMs) and retrieval-augmented generation (RAG) workflows. The speaker will demonstrate how sensitive data, such as personally identifiable information (PII), can be extracted through real-world attacks. This includes techniques like model inversion attacks targeting fine-tuned models, and embedding inversion attacks on vector databases, which are key components in RAG architectures that supply private data to LLMs for answering specific queries. We’ll talk about various categories of protections and mitigations, painting a picture of how to work with AI features safely and when they are too dangerous to use.