EncFormer: Secure and Efficient Transformer Inference over Encrypted Data

• URL: http://arxiv.org/abs/2604.09975v1
• Date: Sat, 11 Apr 2026 01:15:07 GMT
• Title: EncFormer: Secure and Efficient Transformer Inference over Encrypted Data
• Abstract summary: Transformer inference in machine-learning-a-service (MLas-a-service) raises privacy concerns for sensitive user inputs.<n>We present EncFormer, a two-party private Transformer inference framework that introduces Stage Compatible Patterns.<n>We 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.
• Score: 21.63908755417832
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Distributed Motion Planning with Safety Guarantees for Self-Reconfiguring Robotic Boats [76.98547580312116]
  This paper proposes a hybrid framework that combines distributed Model Predictive Control (MPC) with Control Barrier Functions (CBFs)<n>To ensure safety in real time, distributed CBF-based filters are applied to enforce inter-agent avoidance.
  arXiv  Detail & Related papers  (2026-07-22T16:37:05Z)
• WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference [56.297697169678095]
  WISV (Wireless-Informed Semantic Verification) is a novel distributed speculative decoding framework.<n>We show that WISV achieves up to a 60.8% increase in accepted length, a 37.3% reduction in interaction rounds, and a 31.4% improvement in end-to-end latency.<n>We validate WISV on a hardware testbed comprising an NVIDIA Jetson AGX Orin and an A40-equipped server.
  arXiv  Detail & Related papers  (2026-04-20T01:29:56Z)
• SecureRouter: Encrypted Routing for Efficient Secure Inference [18.40709699874288]
  We present Secure inference, an end-to-end encrypted routing and inference framework.<n>Secure achieves a latency reduction by 1.95x with negligible accuracy loss.
  arXiv  Detail & Related papers  (2026-04-16T20:18:12Z)
• GLM-OCR Technical Report [65.42028025507491]
  GLM-OCR is an efficient compact model designed for real-world document understanding.<n>It combines a CogViT visual encoder with a GLM language decoder, achieving a strong balance between computational efficiency and recognition performance.<n>Extensive evaluations on public benchmarks and industrial scenarios show that GLM-OCR achieves competitive or state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-03-11T15:55:47Z)
• HHEML: Hybrid Homomorphic Encryption for Privacy-Preserving Machine Learning on Edge [4.623074730653607]
  Privacy-preserving machine learning (PPML) is an emerging topic to handle secure machine learning inference over sensitive data in untrusted environments.<n>Fully homomorphic encryption (FHE) enables computation directly on encrypted data on the server side, but it introduces significant communication and computation overhead on the client side.<n>HHE addresses this limitation by combining symmetric encryption (SE) with FHE to reduce the computational cost on the client side.<n>Our work proposes a hardware-accelerated HHE architecture built around a lightweight symmetric cipher optimized for FHE compatibility.
  arXiv  Detail & Related papers  (2025-10-23T05:51:55Z)
• Breaking the Layer Barrier: Remodeling Private Transformer Inference with Hybrid CKKS and MPC [16.452180247201948]
  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.<n>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.<n>BLB achieves a $21times$ reduction in communication overhead compared to BOLT (S&P'24) and a $2times$ reduction compared to Bumblebee (NDSS'25), along with latency reductions of $13times$ and $1.8
  arXiv  Detail & Related papers  (2025-08-27T02:40:50Z)
• Accelerating Private Large Transformers Inference through Fine-grained Collaborative Computation [8.859237832459876]
  We present FASTLMPI, a new approach to accelerate private TBM inference through fine-grained optimization.<n>Specifically, through the fine-grained co-design of homomorphic encryption and secret sharing, FASTLMPI achieves efficient protocols for matrix multiplication, SoftMax, LayerNorm, and GeLULU.<n>FASTLMPI shows a remarkable 54% to 64% decrease in runtime and an impressive 72.2% reduction in communication costs.
  arXiv  Detail & Related papers  (2024-12-21T08:33:12Z)
• Ditto: Quantization-aware Secure Inference of Transformers upon MPC [5.161569981377991]
  We propose the framework named Ditto to enable more efficient quantization-aware secure Transformer inference. We conduct extensive experiments on Bert and GPT2 models to evaluate the performance of Ditto. The results demonstrate that Ditto is about $3.14sim 4.40times$ faster than MPCFormer and $1.44sim 2.35times$ faster than the state-of-the-art work PUMA.
  arXiv  Detail & Related papers  (2024-05-09T03:28:16Z)
• Parameter-Adaptive Approximate MPC: Tuning Neural-Network Controllers without Retraining [50.00291020618743]
  This work introduces a novel, parameter-adaptive AMPC architecture capable of online tuning without recomputing large datasets and retraining. We showcase the effectiveness of parameter-adaptive AMPC by controlling the swing-ups of two different real cartpole systems with a severely resource-constrained microcontroller (MCU) Taken together, these contributions represent a marked step toward the practical application of AMPC in real-world systems.
  arXiv  Detail & Related papers  (2024-04-08T20:02:19Z)
• Secure Transformer Inference Protocol [15.610303095235372]
  Security of model parameters and user data is critical for Transformer-based services, such as ChatGPT. Recent strides in secure two-party protocols have successfully addressed security concerns in serving Transformer models, but their adoption is practically infeasible due to the prohibitive cryptographic overheads involved. We present STIP, the first secure Transformer inference protocol without any inference accuracy loss.
  arXiv  Detail & Related papers  (2023-11-14T14:37:23Z)
• Towards Semantic Communication Protocols: A Probabilistic Logic Perspective [69.68769942563812]
  We propose a semantic protocol model (SPM) constructed by transforming an NPM into an interpretable symbolic graph written in the probabilistic logic programming language (ProbLog) By leveraging its interpretability and memory-efficiency, we demonstrate several applications such as SPM reconfiguration for collision-avoidance.
  arXiv  Detail & Related papers  (2022-07-08T14:19:36Z)
• Covert Model Poisoning Against Federated Learning: Algorithm Design and Optimization [76.51980153902774]
  Federated learning (FL) is vulnerable to external attacks on FL models during parameters transmissions. In this paper, we propose effective MP algorithms to combat state-of-the-art defensive aggregation mechanisms. Our experimental results demonstrate that the proposed CMP algorithms are effective and substantially outperform existing attack mechanisms.
  arXiv  Detail & Related papers  (2021-01-28T03:28:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.