UniHENN: Designing Faster and More Versatile Homomorphic Encryption-based CNNs without im2col

• URL: http://arxiv.org/abs/2402.03060v3
• Date: Sun, 25 Aug 2024 06:12:41 GMT
• Title: UniHENN: Designing Faster and More Versatile Homomorphic Encryption-based CNNs without im2col
• Authors: Hyunmin Choi, Jihun Kim, Seungho Kim, Seonhye Park, Jeongyong Park, Wonbin Choi, Hyoungshick Kim,
• Abstract summary: Homomorphic encryption (HE) enables privacy-preserving deep learning by allowing computations on encrypted data without decryption. deploying convolutional neural networks (CNNs) with HE is challenging due to the need to convert input data into a two-dimensional matrix for convolution using the im2col technique. UniHENN is a novel HE-based CNN architecture that eliminates the need for im2col, enhancing its versatility and compatibility with a broader range of CNN models.
• Score: 6.496463706588549
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Homomorphic encryption (HE) enables privacy-preserving deep learning by allowing computations on encrypted data without decryption. However, deploying convolutional neural networks (CNNs) with HE is challenging due to the need to convert input data into a two-dimensional matrix for convolution using the im2col technique, which rearranges the input for efficient computation. This restricts the types of CNN models that can be used since the encrypted data structure must be compatible with the specific model. UniHENN is a novel HE-based CNN architecture that eliminates the need for im2col, enhancing its versatility and compatibility with a broader range of CNN models. UniHENN flattens input data to one dimension without using im2col. The kernel performs convolutions by traversing the image, using incremental rotations and structured multiplication on the flattened input, with results spaced by the stride interval. Experimental results show that UniHENN significantly outperforms the state-of-the-art 2D CNN inference architecture named PyCrCNN in terms of inference time. For example, on the LeNet-1 model, UniHENN achieves an average inference time of 30.089 seconds, about 26.6 times faster than PyCrCNN's 800.591 seconds. Furthermore, UniHENN outperforms TenSEAL, an im2col-optimized CNN model, in concurrent image processing. For ten samples, UniHENN (16.247 seconds) was about 3.9 times faster than TenSEAL (63.706 seconds), owing to its support for batch processing of up to 10 samples. We demonstrate UniHENN's adaptability to various CNN architectures, including a 1D CNN and six 2D CNNs, highlighting its flexibility and efficiency for privacy-preserving cloud-based CNN services.

Related papers

• CNN2GNN: How to Bridge CNN with GNN [59.42117676779735]
  We propose a novel CNN2GNN framework to unify CNN and GNN together via distillation. The performance of distilled boosted'' two-layer GNN on Mini-ImageNet is much higher than CNN containing dozens of layers such as ResNet152.
  arXiv  Detail & Related papers  (2024-04-23T08:19:08Z)
• OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation [70.17681136234202]
  We reexamine the design distinctions and test the limits of what a sparse CNN can achieve. We propose two key components, i.e., adaptive receptive fields (spatially) and adaptive relation, to bridge the gap. This exploration led to the creation of Omni-Adaptive 3D CNNs (OA-CNNs), a family of networks that integrates a lightweight module.
  arXiv  Detail & Related papers  (2024-03-21T14:06:38Z)
• High-Resolution Convolutional Neural Networks on Homomorphically Encrypted Data via Sharding Ciphertexts [0.08999666725996974]
  We extend methods for evaluating DCNNs on images with larger dimensions and many channels, beyond what can be stored in single ciphertexts. We show how existing DCNN models can be regularized during the training process to further improve efficiency and accuracy. These techniques are applied to homomorphically evaluate a DCNN with high accuracy on the high-resolution ImageNet dataset, achieving $80.2%$ top-1 accuracy.
  arXiv  Detail & Related papers  (2023-06-15T15:16:16Z)
• INK: Injecting kNN Knowledge in Nearest Neighbor Machine Translation [57.952478914459164]
  kNN-MT has provided an effective paradigm to smooth the prediction based on neighbor representations during inference. We propose an effective training framework INK to directly smooth the representation space via adjusting representations of kNN neighbors with a small number of new parameters. Experiments on four benchmark datasets show that method achieves average gains of 1.99 COMET and 1.0 BLEU, outperforming the state-of-the-art kNN-MT system with 0.02x memory space and 1.9x inference speedup.
  arXiv  Detail & Related papers  (2023-06-10T08:39:16Z)
• Complex Network for Complex Problems: A comparative study of CNN and Complex-valued CNN [0.0]
  Complex-valued convolutional neural networks (CV-CNN) can preserve the algebraic structure of complex-valued input data. CV-CNNs have double the number of trainable parameters as real-valued CNNs in terms of the actual number of trainable parameters. This paper presents a comparative study of CNN, CNNx2 (CNN with double the number of trainable parameters as the CNN), and CV-CNN.
  arXiv  Detail & Related papers  (2023-02-09T11:51:46Z)
• Towards a General Purpose CNN for Long Range Dependencies in $\mathrm{N}$D [49.57261544331683]
  We propose a single CNN architecture equipped with continuous convolutional kernels for tasks on arbitrary resolution, dimensionality and length without structural changes. We show the generality of our approach by applying the same CCNN to a wide set of tasks on sequential (1$mathrmD$) and visual data (2$mathrmD$) Our CCNN performs competitively and often outperforms the current state-of-the-art across all tasks considered.
  arXiv  Detail & Related papers  (2022-06-07T15:48:02Z)
• Exploiting Hybrid Models of Tensor-Train Networks for Spoken Command Recognition [9.262289183808035]
  This work aims to design a low complexity spoken command recognition (SCR) system. We exploit a deep hybrid architecture of a tensor-train (TT) network to build an end-to-end SRC pipeline. Our proposed CNN+(TT-DNN) model attains a competitive accuracy of 96.31% with 4 times fewer model parameters than the CNN model.
  arXiv  Detail & Related papers  (2022-01-11T05:57:38Z)
• SpectralNET: Exploring Spatial-Spectral WaveletCNN for Hyperspectral Image Classification [0.0]
  Hyperspectral Image (HSI) classification using Convolutional Neural Networks (CNN) is widely found in the current literature. We propose SpectralNET, a wavelet CNN, which is a variation of 2D CNN for multi-resolution HSI classification.
  arXiv  Detail & Related papers  (2021-04-01T08:45:15Z)
• A Token-wise CNN-based Method for Sentence Compression [31.9210679048841]
  Sentence compression is a Natural Language Processing (NLP) task aimed at shortening original sentences and preserving their key information. Current methods are largely based on Recurrent Neural Network (RNN) models which suffer from poor processing speed. We propose a token-wise Conal Neural Network, a CNN-based model along with pre-trained Bidirectional Representations from Transformers (BERT) features for deletion-based sentence compression.
  arXiv  Detail & Related papers  (2020-09-23T17:12:06Z)
• Exploring Deep Hybrid Tensor-to-Vector Network Architectures for Regression Based Speech Enhancement [53.47564132861866]
  We find that a hybrid architecture, namely CNN-TT, is capable of maintaining a good quality performance with a reduced model parameter size. CNN-TT is composed of several convolutional layers at the bottom for feature extraction to improve speech quality.
  arXiv  Detail & Related papers  (2020-07-25T22:21:05Z)
• Approximation and Non-parametric Estimation of ResNet-type Convolutional Neural Networks [52.972605601174955]
  We show a ResNet-type CNN can attain the minimax optimal error rates in important function classes. We derive approximation and estimation error rates of the aformentioned type of CNNs for the Barron and H"older classes.
  arXiv  Detail & Related papers  (2019-03-24T19:42:39Z)

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.