CoPriv: Network/Protocol Co-Optimization for Communication-Efficient Private Inference. (arXiv:2311.01737v1 [cs.CR])

Deep neural network (DNN) inference based on secure 2-party computation (2PC)
can offer cryptographically-secure privacy protection but suffers from orders
of magnitude latency overhead due to enormous communication. Previous works
heavily rely on a proxy metric of ReLU counts to approximate the communication
overhead and focus on reducing the ReLUs to improve the communication
efficiency. However, we observe these works achieve limited communication
reduction for state-of-the-art (SOTA) 2PC protocols due to the ignorance of
other linear and non-linear operations, which …

communication computation focus latency magnitude metric network neural network offer optimization party privacy private protection protocol proxy