Originally published at: https://developer.nvidia.com/blog/confidential-computing-on-h100-gpus-for-secure-and-trustworthy-ai/
Hardware virtualization is an effective way to isolate workloads in virtual machines (VMs) from the physical hardware and from each other. This offers improved security, particularly in a multi-tenant environment. Yet, security risks such as in-band attacks, side-channel attacks, and physical attacks can still happen, compromising the confidentiality, integrity, or availability of your data and…
Host Memory is accessed by the GPU using encrypted buffers, can you comment on the key lifecycle aspects of such encrypted session? Also, can you elaborate on what happens at the NVLINK layer when 2+ GPUs join a Confidential VM? Is the GPU-GPU traffic encrypted? how?