Securing Artificial Intelligence (SAI) – Artificial Intelligence Computing Platform Security Framework

Scope

This work item aims to specify a security framework of AI computing platform containing hardware and basic software to protect valuable assets like models and data deployed on AI computing platform when they are used in runtime or stored at rest. The security framework consists of security components in AI computing platform and security mechanisms executed by security components in the platform. By specifying the security framework, AI computing platform can be consolidated against the relevant attack and able to provide security capabilities to facilitate the stakeholders in AI systems to better protect the valuable assets(model/data) on AI computing platform.The study will use SAI-006 as a start point for hardware aspects and avoid overlap with SAI-006. © Copyright 2024, ETSI

External Links