Efficient ML Models for Practical Secure Inference. (arXiv:2209.00411v2 [cs.CR] UPDATED)

ML-as-a-service continues to grow, and so does the need for very strong
privacy guarantees. Secure inference has emerged as a potential solution,
wherein cryptographic primitives allow inference without revealing users'
inputs to a model provider or model's weights to a user. For instance, the
model provider could be a diagnostics company that has trained a
state-of-the-art DenseNet-121 model for interpreting a chest X-ray and the user
could be a patient at a hospital. While secure inference is in principle
feasible …

ml models