On 22nd March 2022, Sequitur Labs announced its turnkey solution to protect NVIDIA Jetson Powered Edge AI models/IoT devices called EmSPARK Security Suite. This release provides trusted applications to secure intellectual AI property and robust security features and functions needed to protect AI models at the edge.
It works in tandem with the NVIDIA JetPack SDK, and includes support for the latest version (JetPack 4.6). In addition to the latest release supporting the NVIDIA JetPack SDK, Sequitur Labs supports the Jetson Nano, Jetson TX2, Jetson Xavier NX, and Jetson AGX Xavier.
The EmSPARK Security Suite comes with access to the latest test software, along with the necessary documentation. “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”, said Philip Attfield, co-founder and CEO of Sequitur Labs.
NVIDIA Jetson is a popular AI computing platform that’s well suited to embedded and edge applications. Although it provides the necessary toolset and features for such applications and provides high-performance AI at the Edge, manufacturers needed to create their own Trusted Execution Environment (TEE) and applications for cryptography, key management, storage, cloud integration, and AI model protection. Sequitur provides all of these functionalities built for NVIDIA Jetson.
“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 Mr Attfield. Developers can now build applications that use secure resources without having to become experts in cryptography and complex chip-level security technologies.
Embedded security is of vital importance in edge applications, especially the protection of AI models at the edge. Sequitur Labs’ EmSPARK Security Suite has security functions that are housed in a microprocessor’s secure memory partition. Some of these functions are:
Data transmission management