Pith. sign in

DeepReShape: Redesigning Neural Networks for Efficient Private Inference

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Prior work on Private Inference (PI) -- inferences performed directly on encrypted input -- has focused on minimizing a network's ReLUs, which have been assumed to dominate PI latency rather than FLOPs. Recent work has shown that FLOPs for PI can no longer be ignored and incur high latency penalties. In this paper, we develop DeepReShape, a technique that optimizes neural network architectures under PI's constraints, optimizing for both ReLUs and FLOPs for the first time. The key insight is strategically allocating channels to position the network's ReLUs in order of their criticality to network accuracy, simultaneously optimizes ReLU and FLOPs efficiency. DeepReShape automates network development with an efficient process, and we call generated networks HybReNets. We evaluate DeepReShape using standard PI benchmarks and demonstrate a 2.1% accuracy gain with a 5.2$\times$ runtime improvement at iso-ReLU on CIFAR-100 and an 8.7$\times$ runtime improvement at iso-accuracy on TinyImageNet. Furthermore, we investigate the significance of network selection in prior ReLU optimizations and shed light on the key network attributes for superior PI performance.

citation-role summary

background 1

citation-polarity summary

fields

cs.CR 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

background 1

representative citing papers

Private, Verifiable, and Auditable AI Systems

cs.CR · 2025-08-27 · conditional · novelty 4.0

A thesis demonstrating partial prototypes for zk-verifiable model evaluation and privacy-preserving retrieval, and arguing these pieces can compose into end-to-end auditable AI systems.

citing papers explorer

Showing 1 of 1 citing paper.

  • Private, Verifiable, and Auditable AI Systems cs.CR · 2025-08-27 · conditional · none · ref 135 · internal anchor

    A thesis demonstrating partial prototypes for zk-verifiable model evaluation and privacy-preserving retrieval, and arguing these pieces can compose into end-to-end auditable AI systems.