Towards Deep Encrypted Training: Low-Latency, Memory-Efficient, and High-Throughput Inference for Privacy-Preserving Neural Networks

• URL: http://arxiv.org/abs/2604.16834v1
• Date: Sat, 18 Apr 2026 04:54:57 GMT
• Title: Towards Deep Encrypted Training: Low-Latency, Memory-Efficient, and High-Throughput Inference for Privacy-Preserving Neural Networks
• Abstract summary: Homomorphic Encryption (HE) enables computation directly on encrypted data, allowing neural network inference without revealing raw inputs.<n>We develop optimized algorithms for batched HE-friendly neural networks.<n>We evaluate our work using HE-friendly ResNet-20 and ResNet-34 models on encrypted datasets.
• Score: 0.09558392439655011
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Privacy-preserving machine learning (PPML) has become increasingly important in applications where sensitive data must remain confidential. Homomorphic Encryption (HE) enables computation directly on encrypted data, allowing neural network inference without revealing raw inputs. While prior works have largely focused on inference over a single encrypted image, batch processing of encrypted inputs lags behind, despite being critical for high-throughput inference scenarios and training-oriented workloads. In this work, we address this gap by developing optimized algorithms for batched HE-friendly neural networks. We also introduced a pipeline architecture designed to maximize resource efficiency for different batch size execution. We implemented these algorithms and evaluated our work using HE-friendly ResNet-20 and ResNet-34 models on encrypted CIFAR-10 and CIFAR-100 datasets, respectively. For ResNet-20, our approach achieves an amortized inference time of 8.86 seconds per image when processing a batch of 512 encrypted images, with a peak memory usage of 98.96 GB. These results represent a 1.78x runtime improvement and a 3.74x reduction in memory usage compared to the state-of-the-art design. For the deeper ResNet-34 model, we achieve an amortized inference time of 28.14 on a batch of 256 encrypted images using 246.78GB of RAM

Related papers

• Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient [52.96232442322824]
  Collaborative Decoding (CoDe) is a novel efficient decoding strategy tailored for the Visual Auto-Regressive ( VAR) framework.<n>CoDe capitalizes on two critical observations: the substantially reduced parameter demands at larger scales and the exclusive generation patterns across different scales.<n>CoDe achieves a 1.7x speedup, slashes memory usage by around 50%, and preserves image quality with only a negligible FID increase from 1.95 to 1.98.
  arXiv  Detail & Related papers  (2024-11-26T15:13:15Z)
• DCT-CryptoNets: Scaling Private Inference in the Frequency Domain [8.084341432899954]
  This paper introduces DCT-CryptoNets, a novel approach that operates directly in the frequency-domain to reduce the burden of computationally expensive non-linear activations.<n>It does so by utilizing the discrete cosine transform (DCT), commonly employed in JPEG encoding, which has inherent compatibility with remote computing services.<n>It demonstrates inference on the ImageNet dataset within 2.5 hours (down from 12.5 hours on equivalent 96-thread compute resources)
  arXiv  Detail & Related papers  (2024-08-27T17:48:29Z)
• Dynamic neural network with memristive CIM and CAM for 2D and 3D vision [57.6208980140268]
  We propose a semantic memory-based dynamic neural network (DNN) using memristor. The network associates incoming data with the past experience stored as semantic vectors. We validate our co-designs, using a 40nm memristor macro, on ResNet and PointNet++ for classifying images and 3D points from the MNIST and ModelNet datasets.
  arXiv  Detail & Related papers  (2024-07-12T04:55:57Z)
• Efficient and accurate neural field reconstruction using resistive memory [52.68088466453264]
  Traditional signal reconstruction methods on digital computers face both software and hardware challenges. We propose a systematic approach with software-hardware co-optimizations for signal reconstruction from sparse inputs. This work advances the AI-driven signal restoration technology and paves the way for future efficient and robust medical AI and 3D vision applications.
  arXiv  Detail & Related papers  (2024-04-15T09:33:09Z)
• Pruning random resistive memory for optimizing analogue AI [54.21621702814583]
  AI models present unprecedented challenges to energy consumption and environmental sustainability. One promising solution is to revisit analogue computing, a technique that predates digital computing. Here, we report a universal solution, software-hardware co-design using structural plasticity-inspired edge pruning.
  arXiv  Detail & Related papers  (2023-11-13T08:59:01Z)
• Toward Practical Privacy-Preserving Convolutional Neural Networks Exploiting Fully Homomorphic Encryption [11.706881389387242]
  Homomorphic encryption (FHE) is a viable approach for achieving private inference (PI) FHE implementation of a CNN faces significant hurdles, primarily due to FHE's substantial computational and memory overhead. We propose a set of optimizations, which includes GPU/ASIC acceleration, an efficient activation function, and an optimized packing scheme.
  arXiv  Detail & Related papers  (2023-10-25T10:24:35Z)
• Rapid-INR: Storage Efficient CPU-free DNN Training Using Implicit Neural Representation [7.539498729072623]
  Implicit Neural Representation (INR) is an innovative approach for representing complex shapes or objects without explicitly defining their geometry or surface structure. Previous research has demonstrated the effectiveness of using neural networks as INR for image compression, showcasing comparable performance to traditional methods such as JPEG. This paper introduces Rapid-INR, a novel approach that utilizes INR for encoding and compressing images, thereby accelerating neural network training in computer vision tasks.
  arXiv  Detail & Related papers  (2023-06-29T05:49:07Z)
• MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning [72.80896338009579]
  We find that the memory bottleneck is due to the imbalanced memory distribution in convolutional neural network (CNN) designs. We propose a generic patch-by-patch inference scheduling, which significantly cuts down the peak memory. We automate the process with neural architecture search to jointly optimize the neural architecture and inference scheduling, leading to MCUNetV2.
  arXiv  Detail & Related papers  (2021-10-28T17:58:45Z)
• Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration [83.84684675841167]
  We propose a novel encoding scheme using -1, +1 to decompose quantized neural networks (QNNs) into multi-branch binary networks. We validate the effectiveness of our method on large-scale image classification, object detection, and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2021-06-18T03:11:15Z)
• Enabling Homomorphically Encrypted Inference for Large DNN Models [1.0679692136113117]
  Homomorphic encryption (HE) enables inference using encrypted data but it incurs 100x--10,000x memory and runtime overheads. Secure deep neural network (DNN) inference using HE is currently limited by computing and memory resources. We explore the feasibility of leveraging hybrid memory systems comprised of DRAM and persistent memory.
  arXiv  Detail & Related papers  (2021-03-30T07:53:34Z)
• Quantitative Analysis of Image Classification Techniques for Memory-Constrained Devices [0.7373617024876725]
  Convolutional Neural Networks, or CNNs, are the state of the art for image classification, but typically come at the cost of a large memory footprint. In this paper, we compare CNNs with ProtoNN, Bonsai and FastGRNN when applied to 3-channel image classification using CIFAR-10. We show that Direct Convolution CNNs perform best for all chosen budgets, with a top performance of 65.7% accuracy at a memory footprint of 58.23KB.
  arXiv  Detail & Related papers  (2020-05-11T09:54:54Z)

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.