TUTTI bootstraps CKKS in under 3 ms on CPU
On 192 threads it restores 1 to 9 levels for 4096 messages in 46 to 83.4 ms, up to 3 times faster than SHIP.
Stories per day · 30 days
3 RSS
Relatedhomomorphic-encryption3bootstrapping1ckks1cryptography1ethereum1evm1fpga1llm-inference1lwe1ntt1privacy1threshold-cryptography1threshold-decryption1
9 stories, newest first · one card per story
Stories tagged #fhe
Perseus enables fast homomorphic inference for LLMs
Perseus is 3.96x faster than other FHE implementations for Llama-3-8B
End-to-end NTT on FPGA accelerates FHE operations
The design transforms 2^16 coefficients every 5.12 μs at 400 MHz and accelerates FHE by 1.8-2.2x.
Tulva: Practical Asynchronous Threshold FHE
Tulva adds practical asynchronous threshold decryption to base FHE schemes, with millisecond EVM-oriented benchmarks.
FBAN: A Fully Homomorphic Encryption Compatible Bottleneck Attention Network for Privacy-Preserving Behavioral Authentication
FBAN enables TFHE-based continuous authentication from touch behavior at 128-bit security.
Shuffling is Not Enough: Breaking Permutation-Based Model Confidentiality in Hybrid FHE Inference
Attack breaks permutation-based model confidentiality in hybrid FHE inference, recovering all ResNet-20 linear layers exactly with d+1 queries per layer.
An Open-Source End-to-End FHE Implementation for Privacy-Preserving Llama 3 8B Inference
Odin runs Llama-3-8B fully homomorphic encrypted inference on a single H100 in 366 seconds, a 4.51x speedup over THOR.
PHAT: PHotonic Accelerator for TFHE
PHAT photonic accelerator using optically addressed phase-change memory speeds TFHE bootstrapping FFTs 2.14x-5.10x over the prior ASIC accelerator.
Google’s open-source HEIR lets AI work with data it can’t see
Google open-sourced HEIR, a compiler toolchain that converts pre-trained AI models to operate on homomorphically encrypted data without exposing it.
2