HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data

• URL: http://arxiv.org/abs/2011.01805v2
• Date: Tue, 7 Dec 2021 12:18:58 GMT
• Title: HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data
• Authors: Ehud Aharoni (1), Allon Adir (1), Moran Baruch (1), Nir Drucker (1), Gilad Ezov (1), Ariel Farkash (1), Lev Greenberg (1), Ramy Masalha (1), Guy Moshkowich (1), Dov Murik (1), Hayim Shaul (1) and Omri Soceanu (1) ((1) IBM Research)
• Abstract summary: Homomorphic Encryption (HE) allows performing computation on encrypted data. We present a simple and intuitive framework that abstracts the packing decision for the user. We explain its underlying data structures and propose a novel algorithm for performing 2D operations.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Privacy-preserving solutions enable companies to offload confidential data to third-party services while fulfilling their government regulations. To accomplish this, they leverage various cryptographic techniques such as Homomorphic Encryption (HE), which allows performing computation on encrypted data. Most HE schemes work in a SIMD fashion, and the data packing method can dramatically affect the running time and memory costs. Finding a packing method that leads to an optimal performant implementation is a hard task. We present a simple and intuitive framework that abstracts the packing decision for the user. We explain its underlying data structures and optimizer, and propose a novel algorithm for performing 2D convolution operations. We used this framework to implement an HE-friendly version of AlexNet, which runs in three minutes, several orders of magnitude faster than other state-of-the-art solutions that only use HE.

Related papers

• FastFHE: Packing-Scalable and Depthwise-Separable CNN Inference Over FHE [8.949311128871928]
  We propose FastFHE to accelerate the model inference while simultaneously high inference accuracy over fully homomorphic encryption.<n>First, we propose a new scalable ciphertext data-packing scheme to save the time and storage consumptions.<n>Third, we figure out a BN dot-product fusion matrix to merge the ciphertext convolutional layer with the batch-normalization layer without incurring extra multiplicative depth.
  arXiv  Detail & Related papers  (2025-11-27T13:14:42Z)
• Re-Densification Meets Cross-Scale Propagation: Real-Time Neural Compression of LiDAR Point Clouds [83.39320394656855]
  LiDAR point clouds are fundamental to various applications, yet high-precision scans incur substantial storage and transmission overhead.<n>Existing methods typically convert unordered points into hierarchical octree or voxel structures for dense-to-sparse predictive coding.<n>Our framework comprises two lightweight modules. First, the Geometry Re-Densification Module re-densifies encoded sparse geometry, extracts features at denser scale, and then re-sparsifies the features for predictive coding.
  arXiv  Detail & Related papers  (2025-08-28T06:36:10Z)
• CryptoUNets: Applying Convolutional Networks to Encrypted Data for Biomedical Image Segmentation [0.0]
  We demonstrate the feasibility of a privacy-preserving U-Net deep learning inference framework, namely, homomorphic encryption-based U-Net inference. To our knowledge, this is the first work to achieve support perform implement enable U-Net inference entirely based on homomorphic encryption.
  arXiv  Detail & Related papers  (2025-04-30T11:37:22Z)
• CIPHERMATCH: Accelerating Homomorphic Encryption-Based String Matching via Memory-Efficient Data Packing and In-Flash Processing [8.114331115730021]
  Homomorphic encryption (HE) allows secure computation on encrypted data without revealing the original data. Many cloud computing applications (e.g., DNA read mapping, biometric matching, web search) use exact string matching as a key operation. Prior string matching algorithms that use homomorphic encryption are limited by high computational latency.
  arXiv  Detail & Related papers  (2025-03-12T00:25:58Z)
• At Least Factor-of-Two Optimization for RWLE-Based Homomorphic Encryption [0.0]
  Homomorphic encryption (HE) supports certain operations on encrypted data without the need for decryption. HE schemes come with a non-trivial computational overhead that can hamper data-intensive workloads. We present an encryption method we call Zinc" which forgoes the multiple caching process, replacing it with a single scalar addition.
  arXiv  Detail & Related papers  (2024-08-14T05:42:35Z)
• 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)
• GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds [72.60362979456035]
  Masked Autoencoders (MAE) are challenging to explore in large-scale 3D point clouds. We propose a textbfGenerative textbfDecoder for MAE (GD-MAE) to automatically merges the surrounding context. We demonstrate the efficacy of the proposed method on several large-scale benchmarks: KITTI, and ONCE.
  arXiv  Detail & Related papers  (2022-12-06T14:32:55Z)
• Communication-Efficient Adam-Type Algorithms for Distributed Data Mining [93.50424502011626]
  We propose a class of novel distributed Adam-type algorithms (emphi.e., SketchedAMSGrad) utilizing sketching. Our new algorithm achieves a fast convergence rate of $O(frac1sqrtnT + frac1(k/d)2 T)$ with the communication cost of $O(k log(d))$ at each iteration.
  arXiv  Detail & Related papers  (2022-10-14T01:42:05Z)
• CryptoGCN: Fast and Scalable Homomorphically Encrypted Graph Convolutional Network Inference [12.03953896181613]
  Cloud-based graph convolutional network (GCN) has demonstrated great success and potential in many privacy-sensitive applications. Despite its high inference accuracy and performance on cloud, maintaining data privacy in GCN inference remains largely unexplored. In this paper, we take an initial attempt towards this and develop $textitCryptoGCN$--a homomorphic encryption (HE) based GCN inference framework.
  arXiv  Detail & Related papers  (2022-09-24T02:20:54Z)
• THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption [112.02441503951297]
  Privacy-preserving inference of transformer models is on the demand of cloud service users. We introduce $textitTHE-X$, an approximation approach for transformers, which enables privacy-preserving inference of pre-trained models.
  arXiv  Detail & Related papers  (2022-06-01T03:49:18Z)
• Efficient Encrypted Inference on Ensembles of Decision Trees [21.570003967858355]
  Data privacy concerns often prevent the use of cloud-based machine learning services for sensitive personal data. We propose a framework to transfer knowledge extracted by complex decision tree ensembles to shallow neural networks. Our system is highly scalable and can perform efficient inference on batched encrypted (134 bits of security) data with amortized time in milliseconds.
  arXiv  Detail & Related papers  (2021-03-05T01:06:30Z)
• KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation [71.79090083883403]
  "Traditional" encoder-decoder based approaches perform poorly in detecting smaller structures and are unable to segment boundary regions precisely. We propose KiU-Net which has two branches: (1) an overcomplete convolutional network Kite-Net which learns to capture fine details and accurate edges of the input, and (2) U-Net which learns high level features. The proposed method achieves a better performance as compared to all the recent methods with an additional benefit of fewer parameters and faster convergence.
  arXiv  Detail & Related papers  (2020-10-04T19:23:33Z)
• EfficientFCN: Holistically-guided Decoding for Semantic Segmentation [49.27021844132522]
  State-of-the-art semantic segmentation algorithms are mostly based on dilated Fully Convolutional Networks (dilatedFCN) We propose the EfficientFCN, whose backbone is a common ImageNet pre-trained network without any dilated convolution. Such a framework achieves comparable or even better performance than state-of-the-art methods with only 1/3 of the computational cost.
  arXiv  Detail & Related papers  (2020-08-24T14:48:23Z)
• Unsupervised Deep Cross-modality Spectral Hashing [65.3842441716661]
  The framework is a two-step hashing approach which decouples the optimization into binary optimization and hashing function learning. We propose a novel spectral embedding-based algorithm to simultaneously learn single-modality and binary cross-modality representations. We leverage the powerful CNN for images and propose a CNN-based deep architecture to learn text modality.
  arXiv  Detail & Related papers  (2020-08-01T09:20:11Z)
• New Oracle-Efficient Algorithms for Private Synthetic Data Release [52.33506193761153]
  We present three new algorithms for constructing differentially private synthetic data. The algorithms satisfy differential privacy even in the worst case. Compared to the state-of-the-art method High-Dimensional Matrix Mechanism citeMcKennaMHM18, our algorithms provide better accuracy in the large workload.
  arXiv  Detail & Related papers  (2020-07-10T15:46:05Z)
• Faster Secure Data Mining via Distributed Homomorphic Encryption [108.77460689459247]
  Homomorphic Encryption (HE) is receiving more and more attention recently for its capability to do computations over the encrypted field. We propose a novel general distributed HE-based data mining framework towards one step of solving the scaling problem. We verify the efficiency and effectiveness of our new framework by testing over various data mining algorithms and benchmark data-sets.
  arXiv  Detail & Related papers  (2020-06-17T18:14:30Z)

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.