{"ID":2872023,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.09107","arxiv_id":"2509.09107","title":"CryptGNN: Enabling Secure Inference for Graph Neural Networks","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.","short_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 compu...","url_abs":"https://arxiv.org/abs/2509.09107","url_pdf":"https://arxiv.org/pdf/2509.09107v1","authors":"[\"Pritam Sen\",\"Yao Ma\",\"Cristian Borcea\"]","published":"2025-09-11T02:35:33Z","proceeding":"cs.CR","tasks":"[\"cs.CR\",\"cs.LG\"]","methods":"[\"Graph Neural Network\"]","has_code":false}