Entrada to Secure Graph Convolutional Networks ¹

Graph convolutional networks (GCNs) are gaining popularity due to their powerful modelling capabilities. However, guaranteeing privacy is an issue when evaluating on inputs that contain users' sensitive information such as social interactions, financial transactions, etc. To address such privacy concerns, we design <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathsf {Entrada}$</tex-math></inline-formula>, a framework for securely evaluating GCNs that relies on the technique of secure multiparty computation (MPC). For efficiency and accuracy reasons, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathsf {Entrada}$</tex-math></inline-formula> builds over 4-party MPC framework of Tetrad (NDSS'22) and enhances it by providing necessary primitives. Moreover, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathsf {Entrada}$</tex-math></inline-formula> leverages GraphSC paradigm of Araki et al. (CCS'21) to further enhance efficiency. To leverage the GraphSC paradigm, we (i) identify computations in GCN evaluation that benefit from GraphSC, and (ii) define <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathsf {Scatter}\PLXtext{-}\mathsf {Gather}$</tex-math></inline-formula> primitives of GraphSC specific to the identified computations. Further, as required for GraphSC, we design a secure and efficient shuffle protocol in the 4-party setting, which to the best of our knowledge, is done for the first time and may be of independent interest. Through extensive experiments, we showcase secure GCN's accuracy evaluated via <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathsf {Entrada}$</tex-math></inline-formula> is on par with its cleartext counterpart. We benchmark efficiency of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathsf {Entrada}$</tex-math></inline-formula> with respect to the included primitives as well as the framework as a whole. Finally, we showcase <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathsf {Entrada}$</tex-math></inline-formula>'s practicality by benchmarking GCN-based fraud detection applications.