MEDS

Abstract Comparisons are an essential component of Rectified Linear Unit functions (ReLU's), ever more present in Machine Learning, specifically in Neural Networks. Motivated by the increasing interest in privacy-preserving Artificial Intelligence, we explore the current state of the art in Multi-Party Computation (MPC) protocols for privacy preserving comparisons. We systematize them, and introduce constant round variations that are compatible with customary fixed point arithmetic over MPC. Furthermore, we provide novel combinations, inspired by popular comparison protocols, equipped with state of the art elements. Our main focus is implementation and benchmarking; hence, we translate our results into practice via an open source library, compatible with current MPC software tools, showcasing our contributions. Additionally, we include a comprehensive comparative study on various adversarial settings. Indeed, our results improve running times in practical scenarios. Finally, we offer..