The FHE Inference Wall
Log-scale bar chart comparing FHE vs MPC inference latency for BERT-Tiny, BERT-Base, ResNet-20, and ResNet-50. Click a model to see memory and throughput detail.
⬢ loading artifact…
Appears in
The Bootstrapping Tax: FHE's Fundamental Limit on Private AI Inference
BERT-base under FHE takes 149 seconds, needs 112 GB, and sustains 0.007 samples/sec. Best-case MPC takes 2.3 seconds and 4 GB. The gap traces to one operation: bootstrapping — the noise-refresh that makes FHE theoretically unlimited but practically expensive.
7 min read ⬢ interactive