EncFormer: Secure and Efficient Transformer Inference over Encrypted Data

Computer Science > Cryptography and Security [Submitted on 11 Apr 2026] EncFormer: Secure and Efficient Transformer Inference over Encrypted Data Yufan Zhu, Chao Jin, Khin Mi Mi Aung, Xiaokui Xiao Transformer inference in machine-learning-as-a-service (MLaaS) raises privacy concerns for sensitive user inputs. Prior secure solutions that combine fully homomorphic encryption (FHE) and secure multiparty computation (MPC) are bottlenecked by inefficient FHE kernels, communication-heavy MPC protocols, and expensive FHE-MPC conversions. We present EncFormer, a two-party private Transformer inference framework that introduces Stage Compatible Patterns so that FHE kernels compose efficiently, reducing repacking and conversions. EncFormer also provides a cost analysis model built around a minimal-conversion baseline, enabling principled selection of FHE-MPC boundaries. To further reduce communication, EncFormer proposes a secure complex CKKS-MPC conversion protocol and designs communication-efficient MPC protocols for nonlinearities. With GPU optimizations, evaluations on GPT- and BERT-style models show that EncFormer achieves 1.4x-30.4x lower online MPC communication and 1.3x-9.8x lower end-to-end latency against prior hybrid FHE-MPC systems, and 1.9x-3.5x lower end-to-end latency on BERT-base than FHE-only pipelines under a matched backend, while maintaining near-plaintext accuracy on selected GLUE tasks. Comments: 22 pages, 9 figures. Manuscript submitted to IEEE TDSC Subjects: Cryptography and Security (cs.CR) ACM classes: C.2.4; I.2.7; E.3 Cite as: arXiv:2604.09975 [cs.CR]   (or arXiv:2604.09975v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.09975 Focus to learn more Submission history From: Yufan Zhu [view email] [v1] Sat, 11 Apr 2026 01:15:07 UTC (2,586 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 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?)