Speed of inference for various networks
How Zama’ Hosted Service Works
Upload your trained neural network to our hosting service.
Our homomorphic compiler will convert it into an end-to-end encrypted equivalent, optimizing parameters to maximize security while minimizing latency
Encrypt your input data using the client SDK, and send your request to the API endpoint generated by the compiler.
Our distributed, hardware-accelerated infrastructure will run your query encrypted using our open-source cryptographic library, and send back an encrypted result. Everything is done using homomorphic encryption, meaning our servers can never see the data it processes.
Decrypt the result using the client SDK. You have now made an end-to-end encrypted prediction, without any changes to your product UX and architecture!