Paper

General Techniques for Reducing Key-Switching Overhead in Privacy-Preserving Two-Party Transformer Inference

Unreadunread

AI summary

arXiv:2606. 25349v1 Announce Type: new Abstract: In secure two-party Transformer inference, linear layers are typically evaluated using Fully Homomorphic Encryption (FHE) through plaintext-ciphertext or ciphertext-ciphertext matrix multiplications, where key switching primarily occurs and dominates computational overhead in both FHE-based and hybrid FHE-MPC systems.

Reading status

Priority

About this paper

Authors: Wenshao Yang, Zhenhua Liu, Dongdong Yao
Released: 2026-06-25 (14d ago)
Topic: Related to current project
Relation to my work: Read next because General Techniques for Reducing Key-Switching Overhead in Privacy-Preserving Two-Party Transformer Inference overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: text, under, eval, source, line, rate, without, full. Source: arxiv cs.CR (Cryptography and Security).
arXiv: 2606.25349

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to General Techniques for Reducing Key-Switching Overhead in Privacy-Preserving Two-Party Transformer Inference. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.