arXiv AI October 27, 2026 By Yang Li, Gang He, Ruichen Zhang, Guangyuan Liu, Yinqiu Liu

Pacifo: An Efficient Fully Homomorphic Encryption-based Lightweight ResNet for Trustworthy Machine Learning as a Service

Pacifo is a framework that adapts fine‑tuning strategies to efficiently run the ResNet20 model using Fully Homomorphic Encryption (FHE). It introduces a public‑private layer partitioning scheme and an efficient ReLU approximation, reducing private layers and costly FHE operations during inference. Compared to state‑of‑the‑art FHE implementations, Pacifo achieves a 3.7–21.7× speedup while preserving 95–99 % of the original plaintext model accuracy.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Oct 19

Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption

arXiv:2509.01253v2 Announce Type: replace-cross Abstract: In contemporary cloud-based services, protecting users' sensitive data and ensuring the confidentiality of the server's model are critical. F...

By Sayan Biswas, Philippe Chartier, Akash Dhasade, Tom Jurien, David Kerriou, Anne-Marie Kerrmarec, Mohammed Lemou, Franklin Tranie, Martijn de Vos, Milos Vujasinovic

efficiency benchmarks

arXiv Machine Learning

Jun 16

FEnc$^2$: Unifying Data Packing for Efficient Private Inference via Convolution and Architecture-Aware Fragment Encoding

arXiv:2606. 16359v1 Announce Type: cross Abstract: Fully Homomorphic Encryption (FHE) enables privacy-preserving machine learning but incurs extreme computational and memory overhead.

By Ran Ran, Zhaoting Gong, Nuo Xu, Yuanchao Xu, Fan Yao, Wujie Wen

benchmarks safety

arXiv AI

Sep 3

HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation

HEAT introduces a fine‑tuning method that treats the number of iterations used to approximate nonlinearities in fully homomorphic encryption (FHE) as learnable parameters, allowing them to co‑adapt with model weights. By optimizing iteration counts per nonlinearity, HEAT reduces the required iterations, bootstraps, and overall latency for encrypted GPT‑2 decoding while improving decode agreement. The approach achieves a 3.1× reduction in iterations, a 1.6× reduction in bootstraps, and a 1.4× speed‑up in end‑to‑end latency without changing the model architecture or requiring retraining from scratch.

By Alessandro Zirilli, Davide Marincione, Evgenios M. Kornaropoulos, Giuseppe Ateniese, Emanuele Rodol\`a

llms fine-tuning

arXiv AI

Jul 9

PRoVeFL: Private Robust and Verifiable Aggregation in Federated Learning

arXiv:2607. 06612v1 Announce Type: cross Abstract: Federated Learning (FL) enables multiple clients to collaboratively train machine learning models while retaining data locality, thereby enhancing user privacy.

By Harsh Kasyap, Anil Kumar Pradhan, Ugur Ilker Atmaca, Graham Cormode, Carsten Maple

benchmarks safety

arXiv Machine Learning

Sep 16

OptiPrime: Optimizing Private Inference through Protocol-Hardware Co-design

arXiv:2609.16898v1 Announce Type: cross Abstract: Private deep neural network (DNN) inference based on hybrid homomorphic encryption (HE) and multi-party computation (MPC) can protect user data with...

By Jiangrui Yu, Ye Yu, Si Chen, Chenqi Lin, Wenxuan Zeng, Junfeng Fan, Mingyu Gao, Meng Li

benchmarks

Hugging Face Trending Papers

Jul 7

PRoVeFL: Private Robust and Verifiable Aggregation in Federated Learning

Federated Learning (FL) enables multiple clients to collaboratively train machine learning models while retaining data locality, thereby enhancing user privacy. However, traditional FL frameworks rely on a centralized aggregation server and assume honest-but-curious clients, making them susceptible to both server-side inference and client-side poisoning attacks.

benchmarks safety

One email a morning, machine-written

Related stories

Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption

FEnc$^2$: Unifying Data Packing for Efficient Private Inference via Convolution and Architecture-Aware Fragment Encoding

HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation

PRoVeFL: Private Robust and Verifiable Aggregation in Federated Learning

OptiPrime: Optimizing Private Inference through Protocol-Hardware Co-design

PRoVeFL: Private Robust and Verifiable Aggregation in Federated Learning