Securing AI Workloads: Building Zero-Trust Architecture for LLM Appl... Rohit Ghumare & Joinal Ahmed
Rohit Ghumare, Joinal Ahmed
KubeCon + CloudNativeCon Europe 2025 · Session
In an era where Large Language Models (LLMs) are rapidly integrating into virtually every sector, the security implications of these powerful AI applications are becoming increasingly critical. This talk, delivered by Rohit Ghumare and Joinal Ahmed at KubeCon EU, addresses the urgent need for robust security architectures in LLM deployments. The presentation delves into the inherent vulnerabilities of LLM applications, from their underlying infrastructure to the application layer, and proposes a comprehensive **zero-trust architecture** as the foundational solution.
AI review
This session delivers a robust and actionable framework for securing Large Language Model (LLM) applications using a zero-trust architecture. While the core security concepts aren't novel, their specific application to the rapidly evolving LLM threat landscape, including the introduction of the 'AI Gateway' as a critical control point, is timely and highly impactful. The speakers effectively highlight real-world incidents and provide a comprehensive overview of tools and strategies, making it invaluable for anyone deploying LLMs in production.