Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

FuseFSS: Efficient Secure LLM Inference with Function Secret Sharing

About

Two-server secure inference allows a client to query a hosted large language model (LLM) without revealing prompts or embeddings. Recent GPU systems based on function secret sharing (FSS) make linear layers efficient, but fixed-point nonlinearities and helper operations remain a bottleneck because each operator is typically implemented as a bespoke protocol with its own comparisons, wrap-around corrections, and preprocessing material. We present FuseFSS, a compiler that replaces per-operator protocol design with a single compilation pipeline. For each scalar fixed-point operator, a compact specification lists its interval partition, low-degree arithmetic pieces, and required predicate bits. The compiler emits two batched FSS evaluations on the public masked value: one packed comparison that returns all predicate bits, and one vector interval lookup that returns the active coefficients and constants. Compared to the current state-of-the-art FSS-based GPU secure inference, FuseFSS preserves accuracy while achieving a $1.24\times$--$1.50\times$ end-to-end speedup and reducing online communication by $9\%$--$16\%$ on BERT and GPT-style models; preprocessing is also lighter, with $14\%$--$23\%$ lower key-generation time and $20\%$--$24\%$ smaller keys.

Yuhan Ma, Yong Li, Stefan Schmid• 2026

Related benchmarks

TaskDatasetResultRank
Secure InferenceTransformer Models
Online Time (ms)42.6
10
Natural Language UnderstandingGLUE
SST-2 Accuracy92.5
6
Secure LLM InferenceLLaMA 7B--
3
Secure LLM InferenceLlama 8B 3.1--
3
Showing 4 of 4 rows

Other info

Follow for update