On Polynomial Approximations for Privacy-Preserving and Verifiable ReLU Networks

Outsourcing deep neural networks (DNNs) inference tasks to an untrusted cloud raises data privacy and integrity concerns. While there are many techniques to ensure privacy and integrity for polynomial-based computations, DNNs involve non-polynomial computations. To address these challenges, several privacy-preserving and verifiable inference techniques have been proposed based on replacing the non-polynomial activation functions such as the rectified linear unit (ReLU) function with polynomial activation functions. Such techniques usually require polynomials with integer coefficients or polynomials over finite fields. Motivated …

address challenges cloud cs.cr cs.it cs.lg data data privacy integrity math.it networks neural networks non outsourcing privacy techniques untrusted