paper-with-me

Papers

Penguin: Parallel-Packed Homomorphic Encryption for Fast Graph Convolutional Network Inference

2023-09-21 · NeurIPS 2023 11

The marriage of Graph Convolutional Network (GCN) and Homomorphic Encryption (HE) enables the inference of graph data on the cloud with significantly enhanced client data privacy. However, the tremendous computation and memory overhead associated with HE operations challenges the practicality of HE-based GCN inference. GCN inference involves a sequence of expensive matrix-matrix multiplications, and we observe that directly applying the state-of-the-art HE-based secure matrix-matrix multiplication solutions to accelerate HE-GCN inference is far less efficient as it does not exploit the unique aggregation mechanism of two-dimension graph node-features in GCN layer computation. As a result, in this paper, we propose a novel HE-based ciphertext packing technique, i.e., Penguin, that can take advantage of the unique computation pattern during the HE-GCN inference to significantly reduce the computation and memory overhead associated with HE operations. Specifically, Penguin employs (i) an effective two-dimension parallel packing technique for feature ciphertext with optimal graph node partitioning and graph feature interleaving, and (ii) an interleaved assembly technique that can effectively make use of the blank slots to merge ciphertexts after feature reduction and significantly reduce the costly rotation operation. We provide theoretical analysis and experimental validation to demonstrate the speedup achieved by Penguin in accelerating GCN inference using popular GCN models and datasets. Our results show that Penguin can achieve up to $\sim10\times$ speedup and around $\sim79$% reduction in computational memory overhead, significantly outperforming state-of-the-art solutions. To the best of our knowledge, this is the first work that can ensure the protection of both graph structure and features when accelerating HE-GCN inference on encrypted data. Our code is publicly available at https://github.com/ranran0523/Penguin.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…

Similar Papers 제목 키워드 기반

TGHE: Template-based Graph Homomorphic Encryption for Privacy-Preserving GNN Inference in Edge-Cloud Systems

2026-06-25 · Ngoc Bao Anh Le, Thai T. Vu, John Le, Heath Cooper 외 arxiv

Existing homomorphic encryption (HE)-based GNN systems adopt a graph-centric paradigm that couples per-query cost to global graph size, limiting evaluations to at most ~20k nodes and making them incompatible with dynamic…

PackVFL: Efficient HE Packing for Vertical Federated Learning

2024-05-01 · Liu Yang, Shuowei Cai, Di Chai, Junxue Zhang 외

As an essential tool of secure distributed machine learning, vertical federated learning (VFL) based on homomorphic encryption (HE) suffers from severe efficiency problems due to data inflation and time-consuming operati…

Federated LearningVertical Federated Learning

HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption

2024-03-21 · Seewoo Lee, Garam Lee, Jung Woo Kim, Junbum Shin 외

Transfer learning is a de facto standard method for efficiently training machine learning models for data-scarce problems by adding and fine-tuning new classification layers to a model pre-trained on large datasets. Alth…

Privacy PreservingTransfer Learning

AEGIS: Scaling Long-Sequence Homomorphic Encrypted Transformer Inference via Hybrid Parallelism on Multi-GPU Systems

2026-04-03 · Zhaoting Gong, Ran Ran, Fan Yao, Wujie Wen arxiv

Fully Homomorphic Encryption (FHE) enables privacy-preserving Transformer inference, but long-sequence encrypted Transformers quickly exceed single-GPU memory capacity because encoded weights are already large and encryp…

Scaling Homomorphic Applications in Deployment

2025-09-30 · Ryan Marinelli, Angelica Chowdhury arxiv

In this endeavor, a proof-of-concept homomorphic application is developed to determine the production readiness of encryption ecosystems. A movie recommendation app is implemented for this purpose and productionized thro…

Reinforcement LearningMovie Recommendation