593 Hits in 4.7 sec

Corella: A Private Multi Server Learning Approach based on Correlated Queries [article]

Hamidreza Ehteram, Mohammad Ali Maddah-Ali, Mahtab Mirmohseni
2020 arXiv   pre-print
Simulation results for various datasets demonstrate the accuracy of the proposed approach for the classification, using deep neural networks, and the autoencoder, as supervised and unsupervised learning  ...  ., a deep neural network). Each server is fed with the client data, added with strong noise, independent from user data.  ...  Moreover, the computation load per server is the same as running a classical learning algorithm, e.g., a deep neural network.  ... 
arXiv:2003.12052v2 fatcat:zbmbcjsln5d3xjynwtckdlg5sa

2021 Index IEEE Transactions on Parallel and Distributed Systems Vol. 32

2022 IEEE Transactions on Parallel and Distributed Systems  
., +, TPDS May 2021 1030-1043 Privacy-Preserving Computation Offloading for Parallel Deep Neural Networks Training.  ...  Gupta, N., +, TPDS March 2021 575-586 Privacy-Preserving Computation Offloading for Parallel Deep Neural Net- works Training.  ... 
doi:10.1109/tpds.2021.3107121 fatcat:e7bh2xssazdrjcpgn64mqh4hb4

Guest Editorial Special Issue on Smart IoT System: Opportunities by Linking Cloud, Edge, and AI

Wangdong Yang, Laurence T. Yang, A. T. Chronopoulos
2021 IEEE Internet of Things Journal  
In the article "D2D-enabled mobile-edge computation offloading for multiuser IoT network," Yang et al. design Digital Object Identifier 10.1109/JIOT.2021 computational offloading schemes in D2D networks  ...  on a hybrid deep learning algorithm which is composed of convolutional neural network (CNN) and recursive neural network (RNN).  ...  terms of architecture, offloading, security and privacy, and applications.  ... 
doi:10.1109/jiot.2021.3092440 fatcat:psdtaq4pdnemvd4zofkj5k3djm

UAV-Assisted Privacy-Preserving Online Computation Offloading for Internet of Things

Dawei Wei, Ning Xi, Jianfeng Ma, Lei He
2021 Remote Sensing  
To cope with this issue, we propose a novel privacy-preserving online computation offloading method for UAV-assisted IoT.  ...  Recently, computation offloading provides a promising way for the UAV to handle complex tasks by deep reinforcement learning (DRL)-based methods.  ...  UAV-Assisted Privacy-Preserving Keywords: Internet of Things (IoT); computation offloading; differential privacy; unmanned aerial Online Computation Offloading for vehicle; deep reinforcement  ... 
doi:10.3390/rs13234853 fatcat:w635xupw7jfmveizpv5j3l57be

Table of contents

2020 IEEE Internet of Things Journal  
Liu 2651 Lightweight Privacy-Preserving Training and Evaluation for Discretized Neural Networks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Ramamohanarao 2611 Joint Optimization of Offloading Utility and Privacy for Edge Computing Enabled IoT . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/jiot.2020.2980610 fatcat:kn42t7osbndatebk62ec6o7sz4

Deep Learning in the Era of Edge Computing: Challenges and Opportunities [article]

Mi Zhang, Faen Zhang, Nicholas D. Lane, Yuanchao Shu, Xiao Zeng, Biyi Fang, Shen Yan, Hui Xu
2020 arXiv   pre-print
However, deep learning-based approaches require a large volume of high-quality data to train and are very expensive in terms of computation, memory, and power consumption.  ...  In this chapter, we describe eight research challenges and promising opportunities at the intersection of computer systems, networking, and machine learning.  ...  As such, the edge offloading scheme creates a trade-off between computation workload, transmission latency, and privacy preservation.  ... 
arXiv:2010.08861v1 fatcat:2lrjtm6nj5b7nbnilkc74jhbea

Wireless AI: Enabling an AI-Governed Data Life Cycle [article]

Dinh C. Nguyen, Peng Cheng, Ming Ding, David Lopez-Perez, Pubudu N. Pathirana, Jun Li, Aruna Seneviratne, Yonghui Li, H. Vincent Poor
2020 arXiv   pre-print
Recent years have seen rapid deployment of mobile computing and Internet of Things (IoT) networks, which can be mostly attributed to the increasing communication and sensing capabilities of wireless systems  ...  Then, for each data-driven AI theme, we present an overview on the use of AI approaches to solve the emerging data-related problems and show how AI can empower wireless network functionalities.  ...  AI Data Privacy [234] Data privacy preservation Neural networks A ML scheme for privacy preservation in mobile data sensing. [235] Different privacy Neural networks A multifunctional data sensing scheme  ... 
arXiv:2003.00866v1 fatcat:dofctwtag5ewhhzaseeukhtxbe

Not Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloud [article]

Ji Wang and Jianguo Zhang and Weidong Bao and Xiaomin Zhu and Bokai Cao and Philip S. Yu
2019 arXiv   pre-print
The increasing demand for on-device deep learning services calls for a highly efficient manner to deploy deep neural networks (DNNs) on mobile devices with limited capacity.  ...  To mitigate this influence, we propose a noisy training method to enhance the cloud-side network robustness to perturbed data.  ...  Privacy issue in deep learning. Deep learning naturally requires users' data to train neural networks and infer results, which raises the privacy issue for sensitive data.  ... 
arXiv:1809.03428v3 fatcat:canyujedrjd3danrscx35ktspy

Federated Learning for Internet of Things: A Comprehensive Survey [article]

Dinh C. Nguyen, Ming Ding, Pubudu N. Pathirana, Aruna Seneviratne, Jun Li, H. Vincent Poor
2021 arXiv   pre-print
data privacy concerns.  ...  , and IoT privacy and security.  ...  Learning DRL Deep Reinforcement Learning SVM Support Vector Machine NN Neural Network DNN Deep Neural Network CNN Convolutional Neural Network RNN Recurrent Neural Networks LSTM Long-short  ... 
arXiv:2104.07914v1 fatcat:b5wsrfcbynel7jqdxpfw4ftwh4

Machine Learning Systems for Intelligent Services in the IoT: A Survey [article]

Wiebke Toussaint, Aaron Yi Ding
2020 arXiv   pre-print
This survey moves beyond existing ML algorithms and cloud-driven design to investigate the less-explored systems, scaling and socio-technical aspects for consolidating ML and IoT.  ...  Deep convolutional neural networks are now widely used for image, video, speech and audio processing, while recurrent neural networks have been successfully used for sequential data, like text.  ...  [65] study trade-off factors to minimize the training time of convolutional neural networks. Based on their findings, they present Omnivore, an optimizer for asynchronous, data parallel training.  ... 
arXiv:2006.04950v3 fatcat:xrjcioqkrrhpvgmwmutiajgfbe

Edge Intelligence: Architectures, Challenges, and Applications [article]

Dianlei Xu, Tong Li, Yong Li, Xiang Su, Sasu Tarkoma, Tao Jiang, Jon Crowcroft, Pan Hui
2020 arXiv   pre-print
We first identify four fundamental components of edge intelligence, namely edge caching, edge training, edge inference, and edge offloading, based on theoretical and practical results pertaining to proposed  ...  The aim of edge intelligence is to enhance the quality and speed of data processing and protect the privacy and security of the data.  ...  Training Acceleration Training a model, especially deep neural networks, is often too computationally intensive, which may result in low training efficiency on edge devices, due to their limited computing  ... 
arXiv:2003.12172v2 fatcat:xbrylsvb7bey5idirunacux6pe

MSDP: multi-scheme privacy-preserving deep learning via differential privacy

Kwabena Owusu-Agyemeng, Zhen Qin, Hu Xiong, Yao Liu, Tianming Zhuang, Zhiguang Qin
2021 Personal and Ubiquitous Computing  
With the migration of a deep neural network (DNN) in the learning experience in HAR, we present a privacy-preserving DNN model known as Multi-Scheme Differential Privacy (MSDP) depending on the fusion  ...  That the accuracy of the models is greatly improved when trained on a large number of datasets from these data providers on the untrusted cloud server is very significant and raises privacy concerns.  ...  Conclusion We conceptually present a privacy-preserving deep neural network MSDP architecture for wearable Internet of Thing devices based on human activity recognition applications by the injection of  ... 
doi:10.1007/s00779-021-01545-0 fatcat:76cojsbamvfwndkm6ni6hhrfj4

Additively Homomorphical Encryption based Deep Neural Network for Asymmetrically Collaborative Machine Learning [article]

Yifei Zhang, Hao Zhu
2020 arXiv   pre-print
For this scheme, we propose a novel privacy-preserving architecture where two parties can collaboratively train a deep learning model efficiently while preserving the privacy of each party's data.  ...  More specifically, we decompose the forward propagation and backpropagation of the neural network into four different steps and propose a novel protocol to handle information leakage in these steps.  ...  We compare the proposed method with two previous studies that have considered privacy-preserved training with homomorphic encryption for deep neural networks.  ... 
arXiv:2007.06849v1 fatcat:brl2ibxphjgdho6eipyyddqyu4

Federated Learning for Internet of Things: A Comprehensive Survey

Dinh C. Nguyen, Ming Ding, Pubudu N. Pathirana, Aruna Seneviratne, Jun Li, H. Vincent Poor
2021 IEEE Communications Surveys and Tutorials  
data privacy concerns.  ...  , and IoT privacy and security.  ...  Each IoT device runs a neural network for packet classification at the line speed of nearby switches in a scalable manner, while preserving privacy of network traces. 4) FL for IoT Localization: FL can  ... 
doi:10.1109/comst.2021.3075439 fatcat:ycq2zydqrzhibfqyo4vzloeoqy

2020 Index IEEE Internet of Things Journal Vol. 7

2020 IEEE Internet of Things Journal  
., Rateless-Code-Based Secure Cooperative Transmission Scheme for Industrial IoT; JIoT July 2020 6550-6565 Jamalipour, A., see Murali, S., JIoT Jan. 2020 379-388 James, L.A., see Wanasinghe, T.R.,  ...  ., +, Lightweight Privacy-Preserving Training and Evaluation for Discretized Neural Networks. Chen, J., +, JIoT April 2020 2663-2678 Local Differential Privacy for Deep Learning.  ...  ., +, JIoT June 2020 4972-4986 Lightweight Privacy-Preserving Training and Evaluation for Discretized Neural Networks.  ... 
doi:10.1109/jiot.2020.3046055 fatcat:wpyblbhkrbcyxpnajhiz5pj74a
« Previous Showing results 1 — 15 out of 593 results