PRISM: Sensitivity-Aware Pruning Improves Reliability and Efficiency of Homomorphic Encryption Neural Networks
A new structured pruning method, Polynomial-Sensitivity-Aware Pruning (PSAP), improves the reliability of neural networks operating under homomorphic encryption by jointly considering weight magnitude, polynomial activation sensitivity, and rotation cost. Experiments across multiple architectures and datasets show that PSAP-pruned models experience significantly fewer catastrophic accuracy drops—limiting such layers to at most two, compared to 5–14 for magnitude-based pruning—reducing worst-case vulnerability by up to 29 times. PSAP also enhances efficiency, reducing rotation operations by up to 45.2% and lowering multiplicative depth, which enables leveled inference without bootstrapping.
Why it matters: This work advances the practicality and reliability of privacy-preserving AI by making encrypted neural network inference both more robust and efficient.
Full story at: arXiv Cryptography and Security ↗