On the Application of Binary Neural Networks in Oblivious Inference
Mohammad Samragh, Siam U. Hussain, Xinqiao Zhang, Ke Wang Huang, Farinaz Koushanfar · 2021
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 Crypt-Flow2, the state-of-the-art in oblivious inference of non-binary DNNs, our approach reaches 2× faster inference at the same accuracy. Compared to XONN, the state-of-the-art in oblivious inference of binary networks, we achieve 2× to 11× faster inference while obtaining higher accuracy.