defense arXiv Sep 11, 2025 · Sep 2025
Pritam Sen, Yao Ma, Cristian Borcea · New Jersey Institute of Technology · Rensselaer Polytechnic Institute
SMPC-based secure GNN inference framework that protects model parameters from clients and client inputs from cloud providers
Model Theft graph
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.
gnn New Jersey Institute of Technology · Rensselaer Polytechnic Institute
ML Security Papers