With years of experience in application security, Mr. Nguyễn Thành Biên – Solutions engineer at F5 – will share practical insights on Generative AI Runtime Security, one of the most critical security challenges as enterprises begin deploying GenAI in real-world operations – where systems are “live” and continuously interacting with users, data, and core platforms.
F5 will highlight often underestimated runtime risks such as prompt injection, API abuse, data leakage, and anomalous behaviors that go beyond initial training scenarios. From there, the session will emphasize the need to shift the security mindset – from “protecting the model” to securing the entire GenAI application lifecycle in real time and at scale.
From a solution perspective, F5 addresses this challenge through its application and API security platform, enabling traffic control, threat detection, and risk mitigation directly at runtime.

The session aims to provide participants with a clear framework for deploying GenAI securely, reliably, and at scale – while ensuring readiness for future growth.