Orion: A Fully Homomorphic Encryption Framework for Deep Learning

• URL: http://arxiv.org/abs/2311.03470v3
• Date: Wed, 12 Feb 2025 20:06:17 GMT
• Title: Orion: A Fully Homomorphic Encryption Framework for Deep Learning
• Authors: Austin Ebel, Karthik Garimella, Brandon Reagen,
• Abstract summary: Fully Homomorphic Encryption (FHE) has the potential to substantially improve privacy and security by enabling computation directly on encrypted data. One of the major challenges facing wide-scale deployment of FHE-secured neural inference is effectively mapping these networks to FHE primitives. In this paper we address these challenges with Orion, a fully-automated framework for private neural inference using FHE.
• Score: 3.0088450191132394
• License:
• Abstract: Fully Homomorphic Encryption (FHE) has the potential to substantially improve privacy and security by enabling computation directly on encrypted data. This is especially true with deep learning, as today, many popular user services are powered by neural networks in the cloud. Beyond its well-known high computational costs, one of the major challenges facing wide-scale deployment of FHE-secured neural inference is effectively mapping these networks to FHE primitives. FHE poses many programming challenges including packing large vectors, managing accumulated noise, and translating arbitrary and general-purpose programs to the limited instruction set provided by FHE. These challenges make building large FHE neural networks intractable using the tools available today. In this paper we address these challenges with Orion, a fully-automated framework for private neural inference using FHE. Orion accepts deep neural networks written in PyTorch and translates them into efficient FHE programs. We achieve this by proposing a novel single-shot multiplexed packing strategy for arbitrary convolutions and through a new, efficient technique to automate bootstrap placement and scale management. We evaluate Orion on common benchmarks used by the FHE deep learning community and outperform state-of-the-art by 2.38x on ResNet-20, the largest network they report. Orion's techniques enable processing much deeper and larger networks. We demonstrate this by evaluating ResNet-50 on ImageNet and present the first high-resolution FHE object detection experiments using a YOLO-v1 model with 139 million parameters. Orion is open-source for all to use at: https://github.com/baahl-nyu/orion

Related papers

• Till the Layers Collapse: Compressing a Deep Neural Network through the Lenses of Batch Normalization Layers [5.008189006630566]
  We introduce a method called textbfTill the textbfLayers textbfCollapse (TLC), which compresses deep neural networks through the lenses of batch normalization layers. We validate our method on popular models such as Swin-T, MobileNet-V2, and RoBERTa, across both image classification and natural language processing (NLP) tasks.
  arXiv  Detail & Related papers  (2024-12-19T17:26:07Z)
• NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals [58.83169560132308]
  We introduce NNsight and NDIF, technologies that work in tandem to enable scientific study of very large neural networks. NNsight is an open-source system that extends PyTorch to introduce deferred remote execution. NDIF is a scalable inference service that executes NNsight requests, allowing users to share GPU resources and pretrained models.
  arXiv  Detail & Related papers  (2024-07-18T17:59:01Z)
• Exploring Green AI for Audio Deepfake Detection [21.17957700009653]
  State-of-the-art audio deepfake detectors leveraging deep neural networks exhibit impressive recognition performance. Deep NLP models produce around 626k lbs of COtextsubscript2 which is equivalent to five times of average US car emission at its lifetime. This study presents a novel framework for audio deepfake detection that can be seamlessly trained using standard CPU resources.
  arXiv  Detail & Related papers  (2024-03-21T10:54:21Z)
• Active search and coverage using point-cloud reinforcement learning [50.741409008225766]
  This paper presents an end-to-end deep reinforcement learning solution for target search and coverage. We show that deep hierarchical feature learning works for RL and that by using farthest point sampling (FPS) we can reduce the amount of points. We also show that multi-head attention for point-clouds helps to learn the agent faster but converges to the same outcome.
  arXiv  Detail & Related papers  (2023-12-18T18:16:30Z)
• Robust Training and Verification of Implicit Neural Networks: A Non-Euclidean Contractive Approach [64.23331120621118]
  This paper proposes a theoretical and computational framework for training and robustness verification of implicit neural networks. We introduce a related embedded network and show that the embedded network can be used to provide an $ell_infty$-norm box over-approximation of the reachable sets of the original network. We apply our algorithms to train implicit neural networks on the MNIST dataset and compare the robustness of our models with the models trained via existing approaches in the literature.
  arXiv  Detail & Related papers  (2022-08-08T03:13:24Z)
• EDLaaS; Fully Homomorphic Encryption Over Neural Network Graphs [7.195443855063635]
  We use the 4th generation Cheon, Kim, Kim and Song (CKKS) FHE scheme over fixed points provided by the Microsoft Simple Encrypted Arithmetic Library (MS-SEAL) We find that FHE is not a panacea for all privacy preserving machine learning (PPML) problems, and that certain limitations still remain, such as model training. We focus on convolutional neural networks (CNNs), fashion-MNIST, and levelled FHE operations.
  arXiv  Detail & Related papers  (2021-10-26T12:43:35Z)
• StereoSpike: Depth Learning with a Spiking Neural Network [0.0]
  We present an end-to-end neuromorphic approach to depth estimation. We use a Spiking Neural Network (SNN) with a slightly modified U-Net-like encoder-decoder architecture, that we named StereoSpike. We demonstrate that this architecture generalizes very well, even better than its non-spiking counterparts.
  arXiv  Detail & Related papers  (2021-09-28T14:11:36Z)
• 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)
• Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets [65.28292822614418]
  Giant formula for simultaneously enlarging the resolution, depth and width provides us a Rubik's cube for neural networks. This paper aims to explore the twisting rules for obtaining deep neural networks with minimum model sizes and computational costs.
  arXiv  Detail & Related papers  (2020-10-28T08:49:45Z)
• ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing [2.6228228854413356]
  AriaNN is a low-interaction privacy-preserving framework for private neural network training and inference on sensitive data. We design primitives for the building blocks of neural networks such as ReLU, MaxPool and BatchNorm. We implement our framework as an extension to support n-party private federated learning.
  arXiv  Detail & Related papers  (2020-06-08T13:40:27Z)
• Firearm Detection and Segmentation Using an Ensemble of Semantic Neural Networks [62.997667081978825]
  We present a weapon detection system based on an ensemble of semantic Convolutional Neural Networks. A set of simpler neural networks dedicated to specific tasks requires less computational resources and can be trained in parallel. The overall output of the system given by the aggregation of the outputs of individual networks can be tuned by a user to trade-off false positives and false negatives.
  arXiv  Detail & Related papers  (2020-02-11T13:58:16Z)

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.