GAZELLE - A Low Latency Framework for Secure Neural Network Inference
Offered By: USENIX via YouTube
Course Description
Overview
Explore a groundbreaking framework for secure neural network inference in this USENIX Security '18 conference talk. Delve into the Gazelle system, which combines homomorphic encryption and two-party computation techniques to address privacy concerns in cloud-based machine learning. Learn about the Gazelle homomorphic encryption library, optimized homomorphic linear algebra kernels, and encryption switching protocols that enable efficient and private neural network predictions. Discover how Gazelle outperforms existing systems in online runtime and offers significant improvements over fully homomorphic approaches. Gain insights into secure computation, homomorphic encryption, and their applications in protecting both client input and server neural network privacy in prediction-as-a-service scenarios.
Syllabus
Intro
Motivation
Secure Computation (2PC)
Secure Neural Network Inference
FHE vs 2PC vs PAHE+2PC
The PAHE Abstraction
Gazelle: Core Library
Gazelle Core - Performance
Convolution Layers
SISO Convolution - Simple
Gazelle Network - Performance
Taught by
USENIX
Related Courses
Fast Secure Computation for Small Population over the InternetAssociation for Computing Machinery (ACM) via YouTube Stacked Garbling for Disjunctive Zero-Knowledge Proofs
TheIACR via YouTube Laconic Conditional Disclosure of Secrets and Applications
IEEE via YouTube Garbling Gadgets for Boolean and Arithmetic Circuits
Association for Computing Machinery (ACM) via YouTube Optimizing Semi-Honest Secure Multiparty Computation for the Internet
Association for Computing Machinery (ACM) via YouTube