Train on the edge with federated learning

XayNet is Xayn’s federated learning backend. We open-sourced our framework so that developers, companies and organisations can also train AI models directly on device and browser level. Build mobile machine learning applications, all from one codebase – lightweight and privacy-preserving.

Documentation Whitepaper Legal Review

How It Works

Privacy via cross-device federated learning

Train your AI models locally on edge devices such as mobile phones, browsers, or even in cars. Federated learning automatically aggregates the local models into a global model. Thus, all insights inherent in the local models are captured, while the user data stays privately on end devices.

Learn More

Security via homomorphic encryption

Aggregate models with the highest security and trust. Xayn’s masking protocol encrypts all models homomorphically. This enables you to aggregate encrypted local models into a global one – without having to decrypt local models at all. This protects private and even the most sensitive data.

Learn More

Scalability and Agnosticism via Rust

Create AI apps that run anywhere, keeping all data private and scale to aggregate AI models of millions of devices, based on asynchronous processing in Rust. Compile our client and SDK to run natively on Android and iOS or WebAssembly for browsers. Foreign Function Interfaces support calls from other languages, such as Dart, Swift, Java, JavaScript or Python.

Learn More