Pith. sign in

REVIEW 5 cited by

AESPA: Accuracy Preserving Low-degree Polynomial Activation for Fast Private Inference

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2201.06699 v2 pith:CCXLGJ6N submitted 2022-01-18 cs.CR cs.LG

Jaiyoung Park , Michael Jaemin Kim , Wonkyung Jung , Jung Ho Ahn This is my paper · ORCID
classification cs.CRcs.LG
keywords accuracyactivationaespapolynomialinferencelow-degreefunctionmodels
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Hybrid private inference (PI) protocol, which synergistically utilizes both multi-party computation (MPC) and homomorphic encryption, is one of the most prominent techniques for PI. However, even the state-of-the-art PI protocols are bottlenecked by the non-linear layers, especially the activation functions. Although a standard non-linear activation function can generate higher model accuracy, it must be processed via a costly garbled-circuit MPC primitive. A polynomial activation can be processed via Beaver's multiplication triples MPC primitive but has been incurring severe accuracy drops so far. In this paper, we propose an accuracy preserving low-degree polynomial activation function (AESPA) that exploits the Hermite expansion of the ReLU and basis-wise normalization. We apply AESPA to popular ML models, such as VGGNet, ResNet, and pre-activation ResNet, to show an inference accuracy comparable to those of the standard models with ReLU activation, achieving superior accuracy over prior low-degree polynomial studies. When applied to the all-RELU baseline on the state-of-the-art Delphi PI protocol, AESPA shows up to 42.1x and 28.3x lower online latency and communication cost.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CryptoFace: End-to-End Encrypted Face Recognition

    cs.CV 2025-08 conditional novelty 7.0 of 10

    CryptoFace performs face verification entirely on encrypted data with FHE, using a patch-based network that cuts inference latency to about 23 minutes per verification.

  2. PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption

    cs.CR 2026-07 conditional novelty 6.0 of 10

    Sensitivity-aware pruning (PSAP) makes CKKS-encrypted ResNet inference more resistant to bit flips while cutting rotations by up to 45% and removing the need for bootstrapping.

  3. CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computation

    cs.CR 2025-11 conditional novelty 6.0 of 10

    An MPC-ML compiler that modularizes and auto-tunes operator approximations, delivering 1.2–1.8x speedups over an optimized baseline under user-set accuracy bounds.

  4. A Training Framework for Optimal and Stable Training of Polynomial Neural Networks

    cs.LG 2025-05 conditional novelty 5.0 of 10

    Boundary loss plus selective gradient clipping lets polynomial neural networks train stably at high degrees and match ReLU accuracy on seven datasets.

  5. Towards Efficient Privacy-Preserving Machine Learning: A Systematic Review from Protocol, Model, and System Perspectives

    cs.CR 2025-07 conditional novelty 4.0 of 10

    A structured survey of PPML efficiency optimizations, grouped into protocol, model, and system levels, with comparisons and future directions.

Pith tools