Re:Nvidia DGX Spark encrypted firmware slows inference speed...
by hhh on Wednesday November 04, 2026 @05:17AM
(#50363504)
There is already DRM for AI. check out nvidia’s docs around hosting proprietary models with encrypted weights
[ Parent
| on HN ]
Re:Nvidia DGX Spark encrypted firmware slows inference speed...
by novaRom on Wednesday November 04, 2026 @05:54AM
(#50363799)
Interestingly it is Microsoft who filed a patent for DRM-style locking of AI models to verified devices (published July 2026): https://patentlyze.com/patent/microsoft-drm-ai-models-explai...
Re:Nvidia DGX Spark encrypted firmware slows inference speed...
by skew-aberration on Wednesday November 04, 2026 @06:17AM
(#50364003)
So they can avoid the embarrassment when Copilot migrates to Qwen 4
Re:Nvidia DGX Spark encrypted firmware slows inference speed...
by jval43 on Wednesday November 04, 2026 @07:18AM
(#50364565)
AI is actually the perfect use case for homomorphic encryption.
I wonder if this space is explored fully enough at the moment.
Aside from some implementation details, it's conceptually much easier than doing it for a SQL database.
Re:Nvidia DGX Spark encrypted firmware slows inference speed...
by bayindirh on Wednesday November 04, 2026 @08:49AM
(#50365481)
That's older than current AI/LLM/NVIDIA wave. Many application specific DSPs probably carry their model weights in an encrypted manner. If not, we would have seen the extremely performant face recognition and tracking models extracted from professional cameras already.