Hi, I am trying to figure out how to perform model inference inside the enclave. I read the tf_trusted_enclave part, but it seems currently there is only a grpc server doing nothing. Do you have any suggestions on how to integrate the computation of model prediction into enclave as well as take into remote attestation into consideration? Thanks and best regards.
Hi, I am trying to figure out how to perform model inference inside the enclave. I read the tf_trusted_enclave part, but it seems currently there is only a grpc server doing nothing. Do you have any suggestions on how to integrate the computation of model prediction into enclave as well as take into remote attestation into consideration? Thanks and best regards.