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

Computer Science > Cryptography and Security [Submitted on 24 Jun 2026] General Techniques for Reducing Key-Switching Overhead in Privacy-Preserving Two-Party Transformer Inference Wenshao Yang, Zhenhua Liu, Dongdong Yao 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. Existing optimizations rely heavily on packing-specific algorithms, limiting their general applicability. Targeting this overhead from a packing-independent perspective, we propose a preprocessing-assisted method for secure attention computation. By decomposing attention into precomputable operations and online interactions, this method reduces online inference-phase key switching without modifying existing packing strategies. However, the first method shifting key switching offline introduces additional storage requirements. To address this, we propose storage-communication trade-off techniques that replace large precomputed ciphertexts with modest online communication, enabling flexible deployment under varying resource constraints. While ciphertext-ciphertext matrix multiplication is offloaded to the preprocessing phase in hybrid schemes and the first layer of FHE-based schemes, these operations still persist in the offline stage and subsequent FHE layers. To further optimize it, we propose a fused key-switch technique targeting the multiplication-followed-by-rotation pattern, which frequently arises in existing RNS-CKKS matrix multiplication schemes. By combining relinearization and rotation into a single procedure, this technique reduces the associated computation costs. Analytical evaluations demonstrate that our proposed techniques significantly reduce online key-switch overhead and provide flexible trade-offs between storage and communication without requiring modifications to existing packing strategies. Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2606.25349 [cs.CR]   (or arXiv:2606.25349v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.25349 Focus to learn more Submission history From: Wenshao Yang [view email] [v1] Wed, 24 Jun 2026 03:33:17 UTC (27 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)