MPC-FLC: Accelerating Private Inference in MPC Through Full Layer Compression
Bo Zhang, Haiyang Yu, Yuwen Chen, Zhen Yang · 2025
In recent years, the focus on data privacy and security has intensified, with Secure Multi-party Computation (MPC) providing privacy protection for data and models at the cost of increased computational demands. While existing studies emphasize the computational requirements of non-linear inference, our findings reveal that linear computations can also significantly impact model speed, especially in resourceconstrained environments. In this work, we introduce MPCFLC, an optimization framework for secure inference models. Our innovative two-stage distillation process, which integrates matrix decomposition with non-linear substitution, achieves a$2.52 \times$speedup in inference with negligible performance degradation. Furthermore, our specially crafted distillation method enhances distillation speed by$1.3 \times$, further minimizing accuracy loss. Experiments conducted on the GLUE dataset validate the effectiveness of our proposed approach.