Secure Evaluation of Quantized Neural Networks

no code implementations • 28 Oct 2019 • Anders Dalskov, Daniel Escudero, Marcel Keller

Prior works provide protocols that only work on fixed-point integers and specialized activation functions, two aspects that are not supported by popular Machine Learning frameworks, and the need for these specialized model representations means that it is hard, and often impossible, to use e. g., TensorFlow to design, train and test models that later have to be evaluated securely.

Image Classification Quantization