# Nvidia Unveils Scale-In for AI Security

> Nvidia launches Scale-In to secure agentic AI factories with in-silicon security.
- Title: Nvidia Unveils Scale-In for AI Security · SiliconANGLE
- Summary: Nvidia launches Scale-In to secure agentic AI factories with in-silicon security.
- Keywords: nvidia, scale-in, ai factories, bluefield-4, doca, agentic ai, enterprise, SiliconANGLE
- Source: SiliconANGLE — https://siliconangle.com/2026/11/12/ai-networking-nvidia-scalein-security-agentic-aifactoriesdatacenters
- Author: Mark Albertson
- Published: 2026-11-12T22:46:33+00:00
- Read time: 1 min
- Topics: nvidia, scale-in, ai factories, bluefield-4, doca, agentic ai, security, technology, enterprise
## Nvidia Unveils Scale-In
Nvidia introduced Scale-In to secure agentic AI factories with purpose-built acceleration.

> In agentic AI, it’s a completely different use case because now we’re dealing with many agents that need to run on the infrastructure
## Scale-In Security Features
Scale-In delivers secure access, high-performance data movement, tenant isolation and predictable performance.
## Gilad Shainer on Security
Shainer emphasized the need for security as agents expand in AI factories.

> You need to increase security because you need to make sure that those agents are contained in their sandbox and are not doing the wrong things
## BlueField-4 Security
BlueField-4 provides in-silicon security engines for out-of-band monitoring.

> You can think about BlueField or Blue-Field-4 as a device that has in-silicon security engines that are working out of band and collecting telemetry from everything
## DOCA Software Platform
DOCA enables rapid creation of secure, accelerated data center applications.
## OpenShell Reference Architecture
OpenShell integrates with BlueField-4 for secure agent execution across enterprise systems.
## Key takeaway

Nvidia introduced Scale-In to enhance security for agentic AI factories using BlueField-4 and DOCA.