{"ID":2877433,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.19525","arxiv_id":"2508.19525","title":"Breaking the Layer Barrier: Remodeling Private Transformer Inference with Hybrid CKKS and MPC","abstract":"This paper presents an efficient framework for private Transformer inference that combines Homomorphic Encryption (HE) and Secure Multi-party Computation (MPC) to protect data privacy. Existing methods often leverage HE for linear layers (e.g., matrix multiplications) and MPC for non-linear layers (e.g., Softmax activation functions), but the conversion between HE and MPC introduces significant communication costs. The proposed framework, dubbed BLB, overcomes this by breaking down layers into fine-grained operators and further fusing adjacent linear operators, reducing the need for HE/MPC conversions. To manage the increased ciphertext bit width from the fused linear operators, BLB proposes the first secure conversion protocol between CKKS and MPC and enables CKKS-based computation of the fused operators. Additionally, BLB proposes an efficient matrix multiplication protocol for fused computation in Transformers. Extensive evaluations on BERT-base, BERT-large, and GPT2-base show that BLB achieves a $21\\times$ reduction in communication overhead compared to BOLT (S\\\u0026P'24) and a $2\\times$ reduction compared to Bumblebee (NDSS'25), along with latency reductions of $13\\times$ and $1.8\\times$, respectively, when leveraging GPU acceleration.","short_abstract":"This paper presents an efficient framework for private Transformer inference that combines Homomorphic Encryption (HE) and Secure Multi-party Computation (MPC) to protect data privacy. Existing methods often leverage HE for linear layers (e.g., matrix multiplications) and MPC for non-linear layers (e.g., Softmax activa...","url_abs":"https://arxiv.org/abs/2508.19525","url_pdf":"https://arxiv.org/pdf/2508.19525v2","authors":"[\"Tianshi Xu\",\"Wen-jie Lu\",\"Jiangrui Yu\",\"Chen Yi\",\"Chenqi Lin\",\"Runsheng Wang\",\"Meng Li\"]","published":"2025-08-27T02:40:50Z","proceeding":"cs.CR","tasks":"[\"cs.CR\"]","methods":"[\"Transformer\"]","has_code":false}