TY - GEN
T1 - CryptGNN
T2 - 32nd ACM SIGSAC Conference on Computer and Communications Security, CCS 2025
AU - Sen, Pritam
AU - Ma, Yao
AU - Borcea, Cristian
N1 - Publisher Copyright:
© 2025 Copyright held by the owner/author(s).
PY - 2025/11/22
Y1 - 2025/11/22
N2 - 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.
AB - 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.
KW - Graph Neural Networks
KW - Machine Learning as a Service
KW - Secure Multi-party Computation
UR - https://www.scopus.com/pages/publications/105023862621
UR - https://www.scopus.com/pages/publications/105023862621#tab=citedBy
U2 - 10.1145/3719027.3765232
DO - 10.1145/3719027.3765232
M3 - Conference contribution
AN - SCOPUS:105023862621
T3 - CCS 2025 - Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security
SP - 291
EP - 305
BT - CCS 2025 - Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security
PB - Association for Computing Machinery, Inc
Y2 - 13 October 2025 through 17 October 2025
ER -