HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation
Quick summary
arXiv:2609.01730v1 Announce Type: cross Abstract: Fully homomorphic encryption (FHE) allows a server to run a language model directly on encrypted user prompts, but current approaches remain prohibitively slow. Ciphertexts natively support only addition, multiplication, and rotation, and multiplications may be composed only to a bounded depth before a costly bootstrapping operation is needed to continue. Every nonlinearity must therefore be approximated by an iterative method, and each iteration uses multiplications. A higher iteration count buys precision but exhausts the available depth fast
Key takeaways
- arXiv:2609.01730v1 Announce Type: cross Abstract: Fully homomorphic encryption (FHE) allows a server to run a language model directly on encrypted user prompts, but current approaches remain prohibitively slow.
- Ciphertexts natively support only addition, multiplication, and rotation, and multiplications may be composed only to a bounded depth before a costly bootstrapping operation is needed to continue.
- Every nonlinearity must therefore be approximated by an iterative method, and each iteration uses multiplications.
Why it matters
This model development creates a new option for users and a new testing obligation for developers. A fixed evaluation set comparing quality, cost and failure behavior is more useful than launch claims.
Member comments