On the Application of Binary Neural Networks in Oblivious Inference

Mohammad Samragh, Siam Hussain, Xinqiao Zhang, Ke Huang, Farinaz Koushanfar; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 4630-4639

This paper explores the application of Binary Neural Networks (BNN) in oblivious inference, a service provided by a server to mistrusting clients. Using this service, a client can obtain the inference result on her data by a trained model held by the server without disclosing the data or leaning the model parameters. We make two contributions to this field. First, we devise light-weight cryptographic protocols designed specifically to exploit the unique characteristics of BNNs. Second, we present dynamic exploration of the runtime-accuracy tradeoff of BNNs in a single-shot training process. While previous works trained multiple BNNs with different computational complexities (which is cumbersome due to the slow convergence of BNNs), we train a single BNN that can perform inference under different computational budgets. Compared to CryptFlow2, the state-of-the-art in oblivious inference of non-binary DNNs, our approach reaches 2x faster inference at the same accuracy. Compared to XONN, the state-of-the-art in oblivious inference of binary networks, we achieve 2x to 11x faster inference while obtaining higher accuracy.