Explore practical cryptographic solutions for secure inference and private benchmarking in this invited talk from the Privacy-Preserving Machine Learning Workshop (PPML) 2024. Delivered by Nishanth Chandran and chaired by Daniel Escudero, the 53-minute presentation delves into cutting-edge techniques for enhancing privacy and security in machine learning applications. Gain insights into the latest advancements in cryptographic methods that protect sensitive data during inference processes and enable private benchmarking of machine learning models. As part of the PPML 2024 event affiliated with Crypto 2024, this talk offers valuable knowledge for researchers, practitioners, and enthusiasts in the fields of cryptography and privacy-preserving machine learning.