Security software protects NVIDIA Jetson AI platform

It features a generally available development kit and pre-built Trusted Applications that provide robust security features and functions needed to protect AI models at the edge.

Expanding Sequitur’s support for the NVIDIA Jetson platform, the latest release features new Trusted Applications supporting tools for protection of AI models on edge devices, and a turnkey evaluation image that can be implemented on the Jetson platform for development and integration. This new release works in concert with the NVIDIA JetPack SDK, including support for the latest version (JetPack 4.6).

NVIDIA JetPack comes with NVIDIA container runtime and a full Linux software development environment.

This allows developers to package their applications for Jetson with all its dependencies into a single container that is designed to work in any deployment.

And it is powered by the same NVIDIA CUDA-X accelerated computing stack used to create breakthrough AI products in such fields as robotics, industrial IoT, healthcare, smart cities and more.

JetPack provides the tools necessary to get started in developing features and functions of edge applications.

However, manufacturers still need to develop their own production-quality Trusted Execution Environment (TEE) and applications for cryptography, key management, storage, cloud integration and AI model protection.

Sequitur provides all of these, pre-built for NVIDIA Jetson, with the EmSPARK Security Suite and the EmPOWER Lifecycle Management platform.

Sequitur Labs’ EmSPARK Security Suite is designed to address solutions in industries where embedded security is paramount, in particular, protection of AI models at the edge.

Supporting security functions for encryption, storage, data transmission and key/certificate management are delivered by EmSPARK and housed in a microprocessor’s secure memory partition. IoT hardware manufacturers use EmSPARK to easily implement device-level security by addressing technical, IP, supply chain and business process challenges.

Developers can build applications that use secure resources without having to become experts in cryptography and complex chip-level security technologies.

"Building a release of EmSPARK for the NVIDIA Jetson platform is part of our commitment to providing a complete array of tools for protecting AI models on edge devices," said Philip Attfield, co-founder and CEO of Sequitur Labs. "With this release, you can access the latest test software with all of the documentation and tools you need. It’s a turnkey solution and it’s easier than ever to quickly integrate tools for securing devices and protecting AI models on the Jetson platform."