OpenVector
  • OpenVector
  • Introduction
    • Our Thesis
    • Our Solution
    • Other Approaches
    • Benchmarks
  • Network Architecture
    • Overview
    • Networking
    • Deploy Compute Node
    • Deploy CoFHE Node
    • Deploy Client Node
  • Quick start
    • Overview
    • Setting up Client Node
    • Encrypting Data
    • Tensor Multiplication
    • Decrypting the Ouput
    • Verifying the Output
    • Running the Program
  • Tutorials
    • Building MLP Block
  • Use Cases
    • Confidential LLM Inference
    • Training on Encrypted Data
    • Vector Search on Encrypted Data
    • Encrypted Data Access Control
  • API references
    • CryptoSystem Interface
    • ClientNode Class
    • ComputeRequest Class
    • ComputeResponse Class
  • PYTHON API REFERENCES
    • Overview
    • Tensor
    • nn.Module
    • nn.Functional
  • Contribution
    • Call for Research
    • CoFHE Library
Powered by GitBook
On this page
  1. Introduction

Overview

Data has three primary states - at rest, in motion, and in computation. When it comes to data security, we have solved data security at rest and in motion through encryption. But data computation still is mostly done today in plaintext leading to data leaks and privacy concerns.

FHE is the most common cryptographic primitive used for confidential data computation but it is too slow to be meaningfully used for most applications today. Recognising this limitation, OpenVector is building a new confidential compute primitive that is 100 times faster than FHE. The first use case it enables uniquely is confidential AI. OpenVector's vision is to build the Compute Layer Security (CLS) protocol to make every computation encrypted by default.

Last updated 5 months ago