Federated learning trains models across distributed participants without sharing raw data. Standard FL aggregates full model updates (expensive, gradient leakage risk). CRT FL: each of 7 participants trains one channel. Aggregation = CRT reconstruction. Four parity channels (mod 9, 11, 13, 17) give free poison detection. Block-diagonal: zero cross-participant gradient leakage. Privacy by algebra, not by protocol.
Seed (sets true weight):
7 participants each learn their channel's weight from private data. CRT reconstructs the global model. All 7 match = exact reconstruction.
Injects 80% corrupted data into the mod-11 participant. Compare clean vs poisoned weights per channel.
Source code · Public domain (CC0)
.ax source compiled to WASM via self-hosting compiler. Zero HTML authored.