English

CryptGNN: Enabling Secure Inference for Graph Neural Networks

Cryptography and Security 2025-09-12 v1 Machine Learning

Abstract

We present CryptGNN, a secure and effective inference solution for third-party graph neural network (GNN) models in the cloud, which are accessed by clients as ML as a service (MLaaS). The main novelty of CryptGNN is its secure message passing and feature transformation layers using distributed secure multi-party computation (SMPC) techniques. CryptGNN protects the client's input data and graph structure from the cloud provider and the third-party model owner, and it protects the model parameters from the cloud provider and the clients. CryptGNN works with any number of SMPC parties, does not require a trusted server, and is provably secure even if P-1 out of P parties in the cloud collude. Theoretical analysis and empirical experiments demonstrate the security and efficiency of CryptGNN.

Keywords

Cite

@article{arxiv.2509.09107,
  title  = {CryptGNN: Enabling Secure Inference for Graph Neural Networks},
  author = {Pritam Sen and Yao Ma and Cristian Borcea},
  journal= {arXiv preprint arXiv:2509.09107},
  year   = {2025}
}
R2 v1 2026-07-01T05:31:19.160Z