scholarly journals AriaNN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing

2021 ◽  
Vol 2022 (1) ◽  
pp. 291-316
Author(s):  
Théo Ryffel ◽  
Pierre Tholoniat ◽  
David Pointcheval ◽  
Francis Bach
Keyword(s):  
Neural Networks ◽  
Secret Sharing ◽  
Hardware Acceleration ◽  
Building Blocks ◽  
Privacy Preserving ◽  
Cryptographic Protocol ◽  
Sensitive Data ◽  
Network Training ◽  
Private Comparison ◽  
Promising Solution

Abstract We propose AriaNN, a low-interaction privacy-preserving framework for private neural network training and inference on sensitive data. Our semi-honest 2-party computation protocol (with a trusted dealer) leverages function secret sharing, a recent lightweight cryptographic protocol that allows us to achieve an efficient online phase. We design optimized primitives for the building blocks of neural networks such as ReLU, MaxPool and BatchNorm. For instance, we perform private comparison for ReLU operations with a single message of the size of the input during the online phase, and with preprocessing keys close to 4× smaller than previous work. Last, we propose an extension to support n-party private federated learning. We implement our framework as an extensible system on top of PyTorch that leverages CPU and GPU hardware acceleration for cryptographic and machine learning operations. We evaluate our end-to-end system for private inference between distant servers on standard neural networks such as AlexNet, VGG16 or ResNet18, and for private training on smaller networks like LeNet. We show that computation rather than communication is the main bottleneck and that using GPUs together with reduced key size is a promising solution to overcome this barrier.

scholarly journals Privacy-Preserving Deep Neural Network Methods: Computational and Perceptual Methods—An Overview

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1367
Author(s):  
Raghida El El Saj ◽  
Ehsan Sedgh Sedgh Gooya ◽  
Ayman Alfalou ◽  
Mohamad Khalil
Keyword(s):  
Neural Networks ◽  
Classification Accuracy ◽  
Deep Neural Networks ◽  
Privacy Preserving ◽  
Sensitive Data ◽  
Encrypted Data ◽  
High Classification Accuracy ◽  
Hide Information ◽  
Network Methods ◽  
Cloud Environments

Privacy-preserving deep neural networks have become essential and have attracted the attention of many researchers due to the need to maintain the privacy and the confidentiality of personal and sensitive data. The importance of privacy-preserving networks has increased with the widespread use of neural networks as a service in unsecured cloud environments. Different methods have been proposed and developed to solve the privacy-preserving problem using deep neural networks on encrypted data. In this article, we reviewed some of the most relevant and well-known computational and perceptual image encryption methods. These methods as well as their results have been presented, compared, and the conditions of their use, the durability and robustness of some of them against attacks, have been discussed. Some of the mentioned methods have demonstrated an ability to hide information and make it difficult for adversaries to retrieve it while maintaining high classification accuracy. Based on the obtained results, it was suggested to develop and use some of the cited privacy-preserving methods in applications other than classification.

scholarly journals SecureNN: 3-Party Secure Computation for Neural Network Training

2019 ◽  
Vol 2019 (3) ◽  
pp. 26-49 ◽  
Author(s):  
Sameer Wagh ◽  
Divya Gupta ◽  
Nishanth Chandran
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Data Privacy ◽  
Network Inference ◽  
Matrix Multiplication ◽  
Building Blocks ◽  
Secure Computation ◽  
Neural Network Training ◽  
Network Training ◽  
Garbled Circuits

Abstract Neural Networks (NN) provide a powerful method for machine learning training and inference. To effectively train, it is desirable for multiple parties to combine their data – however, doing so conflicts with data privacy. In this work, we provide novel three-party secure computation protocols for various NN building blocks such as matrix multiplication, convolutions, Rectified Linear Units, Maxpool, normalization and so on. This enables us to construct three-party secure protocols for training and inference of several NN architectures such that no single party learns any information about the data. Experimentally, we implement our system over Amazon EC2 servers in different settings. Our work advances the state-of-the-art of secure computation for neural networks in three ways: 1. Scalability: We are the first work to provide neural network training on Convolutional Neural Networks (CNNs) that have an accuracy of > 99% on the MNIST dataset; 2. Performance: For secure inference, our system outperforms prior 2 and 3-server works (SecureML, MiniONN, Chameleon, Gazelle) by 6×-113× (with larger gains obtained in more complex networks). Our total execution times are 2 − 4× faster than even just the online times of these works. For secure training, compared to the only prior work (SecureML) that considered a much smaller fully connected network, our protocols are 79× and 7× faster than their 2 and 3-server protocols. In the WAN setting, these improvements are more dramatic and we obtain an improvement of 553×! 3. Security: Our protocols provide two kinds of security: full security (privacy and correctness) against one semi-honest corruption and the notion of privacy against one malicious corruption [Araki et al. CCS’16]. All prior works only provide semi-honest security and ours is the first system to provide any security against malicious adversaries for the secure computation of complex algorithms such as neural network inference and training. Our gains come from a significant improvement in communication through the elimination of expensive garbled circuits and oblivious transfer protocols.

scholarly journals Federated deep learning for detecting COVID-19 lung abnormalities in CT: a privacy-preserving multinational validation study

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Qi Dou ◽  
Tiffany Y. So ◽  
Meirui Jiang ◽  
Quande Liu ◽  
Varut Vardhanabhuti ◽  
...  
Keyword(s):  
Data Privacy ◽  
Medical Training ◽  
External Validation ◽  
Mainland China ◽  
Privacy Preserving ◽  
Generalization Capability ◽  
Major Focus ◽  
Sensitive Data ◽  
Lung Abnormalities ◽  
Medical Image Diagnosis

AbstractData privacy mechanisms are essential for rapidly scaling medical training databases to capture the heterogeneity of patient data distributions toward robust and generalizable machine learning systems. In the current COVID-19 pandemic, a major focus of artificial intelligence (AI) is interpreting chest CT, which can be readily used in the assessment and management of the disease. This paper demonstrates the feasibility of a federated learning method for detecting COVID-19 related CT abnormalities with external validation on patients from a multinational study. We recruited 132 patients from seven multinational different centers, with three internal hospitals from Hong Kong for training and testing, and four external, independent datasets from Mainland China and Germany, for validating model generalizability. We also conducted case studies on longitudinal scans for automated estimation of lesion burden for hospitalized COVID-19 patients. We explore the federated learning algorithms to develop a privacy-preserving AI model for COVID-19 medical image diagnosis with good generalization capability on unseen multinational datasets. Federated learning could provide an effective mechanism during pandemics to rapidly develop clinically useful AI across institutions and countries overcoming the burden of central aggregation of large amounts of sensitive data.

Privacy-preserving cloud computing on sensitive data: A survey of methods, products and challenges

2019 ◽  
Vol 140-141 ◽  
pp. 38-60 ◽  
Author(s):  
Josep Domingo-Ferrer ◽  
Oriol Farràs ◽  
Jordi Ribes-González ◽  
David Sánchez
Keyword(s):  
Cloud Computing ◽  
Privacy Preserving ◽  
Sensitive Data
Sign in / Sign up

Export Citation Format

Share Document