Antelope: Fast and Secure Neural Network Inference

In this paper, we present Antelope, a semi-honest large-scale secure inference system without revealing either clients' data or model parameters. The main contributions of Antelope are new two-party computation (2PC) protocols over a ring Z_2ℓ for non-linear layers, which optimize the online computation and communication overhead thus outperforming the state-of-the-art 2PC systems. Specifically, we reformulate the comparison function as an Equality-to-Zero test followed by multiplication, decoupling the bit-wise rounding dependency in traditional secret sharing-based bit extraction. With this technique, the evaluation of the ReLU non-linear activation function is 1.7×-84.5× faster than existing solutions in online communication cost. We also develop a suite of optimizations that improve the efficiency of secure division protocols, which are tailored to different divisor settings in the neural networks. We extend our protocols to construct efficient implementations for several building blocks such as ReLU, Maxpool, truncation, and Softmax. End-to-end evaluation on realistic ImageNet-scale networks demonstrates that Antelope achieves over 22.3× and 23.0× online runtime speedups in LAN and WAN settings, respectively, without accuracy loss, compared to the state-of-the-art works. © 2025 IEEE.