FOBNN: Fast Oblivious Binarized Neural Network Inference

The superior performance of deep learning has propelled the rise of Deep Learning as a Service, enabling users to transmit their private data to service providers for model execution and inference retrieval. Nevertheless, the primary concern remains safeguarding the confidentiality of sensitive user data while optimizing the efficiency of secure protocols. To address this, we develop a fast oblivious binarized neural network inference framework, FOBNN. Specifically, we customize binarized convolutional neural networks to enhance oblivious inference, design two fast algorithms for binarized convolutions, and optimize network structures experimentally under constrained costs. Initially, we meticulously analyze the range of intermediate values in binarized convolutions to minimize bit representation, resulting in the Bit Length Bounding (BLB) algorithm. Subsequently, leveraging the efficiency of bitwise operations in BLB, we further enhance performance by employing pure bitwise operations for each binary digit position, yielding the Layer-wise Bit Accumulation (LBA) algorithm. Theoretical analysis validates FOBNN's security and indicates up to $2 \times$ improvement in computational and communication costs compared to the state-of-the-art method. We demonstrates our framework's effectiveness in RNA function prediction within bioinformatics. Rigorous experimental assessments confirm that our oblivious inference solutions not only maintain but often exceed the original accuracy, surpassing prior efforts.