🚨 @HorizenLabs just dropped a deep dive on Verifiable Federated Learning. It explores how distributed AI training can move from trust → verification. Here’s how zero-knowledge proofs play a role. A 🧵...

Federated learning lets multiple parties train a model without sharing raw data. 📍Each participant trains locally. 📦 Updates are sent to an aggregator. 🌐 A global model is produced. Privacy improves. But the system still assumes everyone behaves honestly.