HE^2: A Communication-Light Heterogeneous Architecture for Efficient Fully Homomorphic Encryption

• URL: http://arxiv.org/abs/2605.31004v1
• Date: Fri, 29 May 2026 08:38:53 GMT
• Title: HE^2: A Communication-Light Heterogeneous Architecture for Efficient Fully Homomorphic Encryption
• Abstract summary: CKKS, an emerging fully homomorphic encryption scheme, has been promising in privacy-preserving applications.<n> CKKS involves both compute-intensive operators (ComOps) with high computational cost and memory-intensive operators (MemOps) with large memory footprints.<n>We propose $HE2$, a communication-light xPU-xMU heterogeneous FHE accelerator with dataflow graph (DFG) optimization and architecture co-design.
• Score: 15.713680964307736
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: CKKS, an emerging fully homomorphic encryption (FHE) scheme, has been promising in privacy-preserving applications by enabling SIMD fixed-point computations on ciphertexts. Despite its strong security guarantees, CKKS involves both compute-intensive operators (ComOps) with high computational cost and memory-intensive operators (MemOps) with large memory footprints, making existing ASIC-based or NMP-based acceleration approaches suffer from high hardware overhead and limited efficiency. This observation motivates the integration of the architectural advantages of both paradigms into a heterogeneous xPU (ASIC)-xMU (NMP) architecture. However, in such a design, frequent and long-latency heterogeneous communication caused by the dominant keyswitch operator remains a key performance bottleneck. In this paper, we propose $HE^2$, a communication-light xPU-xMU heterogeneous FHE accelerator with dataflow graph (DFG) optimization and architecture co-design. First, we observe that the majority of communication arises at the interface between ModUp/ModDown and neighboring MemOps. To address this, we propose a DFG-level optimization framework to fully exploit the ModUp/ModDown reduction potential of the hoisting algorithm by identifying parallel keyswitch blocks and fusing them for reduced communication frequency. Second, we design an efficient heterogeneous architecture that adopts a group-level pipelined execution to effectively hide communication latency by leveraging the inherent parallelism across decomposed groups. End-to-end evaluation results show that $HE^2$ achieves 1.66$\times$ speedup and 9.23$\times$ lower EDAP (Energy-Delay-Area Product) compared to the state-of-the-art accelerator, with communication stalls accounting for only 6.67% of the total latency.

Related papers

• FPGA Acceleration of Fully Homomorphic Encryption with Adaptive Key Switching [10.382948833881693]
  Key-switching is a major performance bottleneck among Fully Homomorphic Encryption (FHE) operations.<n>Recent cryptographic advances introduce a novel key-switching method (i.e., KLSS) that reduces certain operational complexity but demands higher computational precision than the traditional Hybrid Key Switching (HKS) method.<n>We propose a memory-efficient KLSS datapath that eliminates off-chip ciphertext transfers.<n>We then develop a performance model to analyze and compare the overheads of both KLSS and HKS.
  arXiv  Detail & Related papers  (2026-09-08T20:24:21Z)
• Accelerating Unified Multimodal Models with Core-Expansion Routing and Unified Computation Scheduling [61.28599393707943]
  Unified multimodal models jointly support understanding and generation, but incur substantial redundant computation across tokens, layers, and generation timesteps.<n>We propose a task-shared core scorer and progress-conditioned generation expansions, optimized through generation decomposition and cross-task core alignment.<n> Experiments on two representative UMM architectures demonstrate consistent quality--efficiency improvements across both tasks, retaining 98.03% of dense understanding performance with a 1.93times$ end-to-end inference speedup.
  arXiv  Detail & Related papers  (2026-08-29T14:27:55Z)
• AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization [84.25316984309725]
  Integration of dynamic, sparse structures with parameter-efficient adapters (e.g., LoRA) is a powerful technique for enhancing Large Language Models (LLMs)<n>Despite minimal increases in computational load, the computation latency often skyrockets, leading to decoding speeds slowing by over 2.5 times.<n>AdaFuse is a framework built on a tight co-design between the algorithm and the underlying hardware system to enable efficient dynamic adapter execution.
  arXiv  Detail & Related papers  (2026-03-12T12:46:42Z)
• Bridging Superconducting and Neutral-Atom Platforms for Efficient Fault-Tolerant Quantum Architectures [14.971894680142343]
  We propose a strategic approach to Heterogeneous Quantum Architectures (HQA) that synthesizes the advantages of the superconducting (SC) and neutral atom (NA) platforms.<n>Our designs achieve $752times$ speedup over NA-only baselines on average and reduce the physical qubit footprint by over $10times$ compared to SC-only systems.
  arXiv  Detail & Related papers  (2026-01-15T07:39:05Z)
• Towards a Functionally Complete and Parameterizable TFHE Processor [3.907410857035328]
  TFHE is a fast torus-based fully homomorphic encryption scheme.<n>It provides the fastest bootstrapping operation performance of any other FHE scheme.<n>It suffers from a considerably higher computational overhead for the evaluation of homomorphic circuits.<n>We propose an FPGA-based hardware accelerator for the evaluation of homomorphic circuits.
  arXiv  Detail & Related papers  (2025-10-27T16:16:40Z)
• Edge Collaborative Gaussian Splatting with Integrated Rendering and Communication [69.23838350582764]
  We present edge collaborative (ECO-GS) where each user can switch between a small GS model to guarantee fidelity and a remote large GS model to guarantee fidelity.<n>We propose integrated and communication (IRAC) which jointly optimize low-cost rendering status and edge power allocation.
  arXiv  Detail & Related papers  (2025-10-26T15:33:29Z)
• 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)
• A Scalable Architecture for Efficient Multi-bit Fully Homomorphic Encryption [1.4174227043241145]
  We introduce Taurus, a hardware accelerator designed to enhance the efficiency of multi-bit TFHE computations.<n>Taurus supports ciphertexts up to 10 bits by leveraging novel FFT units and optimizing memory bandwidth through key reuse strategies.<n>Our experiment results demonstrate that Taurus achieves up to 2600x speedup over a CPU, 1200x speedup over a GPU, and up to 7x faster compared to the previous state-of-the-art accelerator.
  arXiv  Detail & Related papers  (2025-09-16T05:00:57Z)
• Joint Transmit and Pinching Beamforming for Pinching Antenna Systems (PASS): Optimization-Based or Learning-Based? [89.05848771674773]
  A novel antenna system ()-enabled downlink multi-user multiple-input single-output (MISO) framework is proposed.<n>It consists of multiple waveguides, which equip numerous low-cost antennas, named (PAs)<n>The positions of PAs can be reconfigured to both spanning large-scale path and space.
  arXiv  Detail & Related papers  (2025-02-12T18:54:10Z)
• EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference [49.94169109038806]
  This paper introduces EPS-MoE, a novel expert pipeline scheduler for MoE that surpasses the existing parallelism schemes.<n>Our results demonstrate at most 52.4% improvement in prefill throughput compared to existing parallel inference methods.
  arXiv  Detail & Related papers  (2024-10-16T05:17:49Z)
• SOCI^+: An Enhanced Toolkit for Secure OutsourcedComputation on Integers [50.608828039206365]
  We propose SOCI+ which significantly improves the performance of SOCI. SOCI+ employs a novel (2, 2)-threshold Paillier cryptosystem with fast encryption and decryption as its cryptographic primitive. Compared with SOCI, our experimental evaluation shows that SOCI+ is up to 5.4 times more efficient in computation and 40% less in communication overhead.
  arXiv  Detail & Related papers  (2023-09-27T05:19:32Z)
• PolyMPCNet: Towards ReLU-free Neural Architecture Search in Two-party Computation Based Private Inference [23.795457990555878]
  Secure multi-party computation (MPC) has been discussed, to enable the privacy-preserving deep learning (DL) computation. MPCs often come at very high computation overhead, and potentially prohibit their popularity in large scale systems. In this work, we develop a systematic framework, PolyMPCNet, of joint overhead reduction of MPC comparison protocol and hardware acceleration.
  arXiv  Detail & Related papers  (2022-09-20T02:47:37Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)

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.