64,135 Hits in 5.9 sec

Chained Anomaly Detection Models for Federated Learning: An Intrusion Detection Case Study

Davy Preuveneers, Vera Rimmer, Ilias Tsingenopoulos, Jan Spooren, Wouter Joosen, Elisabeth Ilie-Zudor
2018 Applied Sciences  
Furthermore, our blockchain-based federated learning solution can be generalized and applied to more sophisticated neural network architectures and other use cases.  ...  on the federated learning, varying between 5 and 15%, while providing full transparency over the distributed training process of the neural network.  ...  Acknowledgments: We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research.  ... 
doi:10.3390/app8122663 fatcat:22w3om3rwnbgjd7nuo3kdbjn3i

Federated Learning for Distributed Spectrum Sensing in NextG Communication Networks [article]

Yi Shi, Yalin E. Sagduyu, Tugba Erpek
2022 arXiv   pre-print
Each sensor receives signals under a specific channel condition depending on its location and trains an individual model of a deep neural network (DNN) accordingly to classify signals.  ...  The results show the feasibility of extending cooperative spectrum sensing over a general multi-hop wireless network through federated learning and indicate its robustness to wireless network effects,  ...  A feedforward neural network (FNN) is used as the deep neural network model at each sensor. The FNN properties are shown in Table I .  ... 
arXiv:2204.03027v1 fatcat:sgo2emj6ffhkxfnuaelxurhm2i

Centralized Machine Learning Versus Federated Averaging: A Comparison using MNIST Dataset

2022 KSII Transactions on Internet and Information Systems  
Hence, this paper implements Federated Averaging with a Deep Neural Network to classify the handwriting image and protect the sensitive data.  ...  Moreover, we compare the centralized machine learning model with federated averaging.  ...  We start with a simple deep learning model using federated averaging in the experiment. The federated averaging had good performance accuracy even with a basic deep learning model.  ... 
doi:10.3837/tiis.2022.02.020 fatcat:dlcf2q52ljacpfkjppxxruzjsu

Bayesian Federated Learning via Predictive Distribution Distillation [article]

Shrey Bhatt, Aishwarya Gupta, Piyush Rai
2022 arXiv   pre-print
This enables us to leverage advances in standard federated learning to Bayesian federated learning as well.  ...  For most existing federated learning algorithms, each round consists of minimizing a loss function at each client to learn an optimal model at the client, followed by aggregating these client models at  ...  In federated learning, the idea of distillation has been used in other works as well, such as federated learning when the client models are of different sizes and the (weighted) averaging does not make  ... 
arXiv:2206.07562v1 fatcat:vwozrscorncadczfzrvnozyd6i

Towards Privacy-Preserving Affect Recognition: A Two-Level Deep Learning Architecture [article]

Jimiama M. Mase, Natalie Leesakul, Fan Yang, Grazziela P. Figueredo, Mercedes Torres Torres
2021 arXiv   pre-print
and use AUs for processing and training, and (2) federated learning (FL) i.e. process raw images in users' local machines (local processing) and send the locally trained models to the main processing  ...  In this paper, we propose a two-level deep learning architecture for affect recognition that uses AUs in level 1 and FL in level 2 to protect users' identities.  ...  For this, we utilise a deep learning Fig. 3 : A non-federated deep learning strategy for affect recognition using action units Fig. 4 : A federated learning approach for affect recognition using images  ... 
arXiv:2111.07344v1 fatcat:s4amzwluezfxlbzyozfse2qwoi

Deep Federated Learning for Autonomous Driving [article]

Anh Nguyen, Tuong Do, Minh Tran, Binh X. Nguyen, Chien Duong, Tu Phan, Erman Tjiputra, Quang D. Tran
2022 arXiv   pre-print
We propose a peer-to-peer Deep Federated Learning (DFL) approach to train deep architectures in a fully decentralized manner and remove the need for central orchestration.  ...  We design a new Federated Autonomous Driving network (FADNet) that can improve the model stability, ensure convergence, and handle imbalanced data distribution problems while is being trained with federated  ...  rate. 3) Federated Averaging: Following [51] , to compute the prediction of models in all silos, we compute the average model θ using weight aggregation from all the local model θ i .  ... 
arXiv:2110.05754v2 fatcat:yr2gz3sd6jg2hmdavidigim4uy

Temporal Weighted Averaging for Asynchronous Federated Intrusion Detection Systems

Shaashwat Agrawal, Aditi Chowdhuri, Sagnik Sarkar, Ramani Selvanambi, Thippa Reddy Gadekallu, Qiangqiang Yuan
2021 Computational Intelligence and Neuroscience  
In this paper, a novel temporal model averaging algorithm is proposed for asynchronous federated learning (AFL).  ...  Federated learning (FL) is an emerging subdomain of machine learning (ML) in a distributed and heterogeneous setup.  ...  Model Architecture. e model used for the client and server models is a four-layer deep neural network as shown in Figure 4 .  ... 
doi:10.1155/2021/5844728 pmid:34956350 pmcid:PMC8709749 fatcat:zgvapqnjinfqvakuxg3jak5x6e

Federated Deep Reinforcement Learning for the Distributed Control of NextG Wireless Networks [article]

Peyman Tehrani, Francesco Restuccia, Marco Levorato
2021 arXiv   pre-print
Specifically, deep RL (DRL), which uses a deep neural network (DNN) as a predictor, has been shown to achieve good performance even in complex environments and with high dimensional inputs.  ...  In this paper, to address these challenges, we propose a federated learning (FL) approach to DRL, which we refer to federated DRL (F-DRL), where base stations (BS) collaboratively train the embedded DNN  ...  In Fig. 4 , the performance of the distributed and federated deep policy gradient algorithms are compared in terms of average per user rate.  ... 
arXiv:2112.03465v1 fatcat:cnnovm7kk5ayfjjrgf6ydwdyve

Federated Deep Learning Architecture for Personalized Healthcare [chapter]

Helen Chen, Shubhankar Mohapatra, George Michalopoulos, Xi He, Ian McKillop
2021 Studies in Health Technology and Informatics  
Using a diabetes dataset, we demonstrate that accuracy and processing efficiencies using federated deep learning architectures are equivalent to the models built on centralized datasets.  ...  in neural network modeling.  ...  Chen et al. / Federated Deep Learning Architecture for Personalized Healthcare 194 H. Chen et al. / Federated Deep Learning Architecture for Personalized Healthcare  ... 
doi:10.3233/shti210147 pmid:34042732 fatcat:3ikfylo5njf4ba3irp2fiixntm

eFedDNN: Ensemble based Federated Deep Neural Networks for Trajectory Mode Inference [article]

Daniel Opoku Mensah and Godwin Badu-Marfo and Ranwa Al Mallah and Bilal Farooq
2022 arXiv   pre-print
Specifically, we designed a novel ensemble-based Federated Deep Neural Network (eFedDNN).  ...  To address this challenge, we use federated learning (FL), a privacy-preserving machine learning technique that aims at collaboratively training a robust global model by accessing users' locally trained  ...  Federated Learning Training Process Our study adopted the Federated Averaging Algorithm (FedAvg) for inferring the travel mode of users using GPS datasets of smartphone travel surveys.  ... 
arXiv:2205.05756v1 fatcat:okt4v2hkpvenzogyq3jflzcgte

SplitAVG: A heterogeneity-aware federated deep learning method for medical imaging [article]

Miao Zhang, Liangqiong Qu, Praveer Singh, Jayashree Kalpathy-Cramer, Daniel L. Rubin
2022 arXiv   pre-print
Federated learning is an emerging research paradigm for enabling collaboratively training deep learning models without sharing patient data.  ...  We find that the performance of models trained using all the comparison federated learning methods degraded significantly with the increasing degrees of data heterogeneity.  ...  Architecture of Split Averaging (SplitAVG): A deep learning network is split into two sub-networks at a pre-defined cut layer.  ... 
arXiv:2107.02375v5 fatcat:gaqpo5ftrjemhibffhwhqxhrqe

FADL:Federated-Autonomous Deep Learning for Distributed Electronic Health Record [article]

Dianbo Liu, Timothy Miller, Raheel Sayeed, Kenneth D. Mandl
2018 arXiv   pre-print
We propose a new method, called Federated-Autonomous Deep Learning (FADL) that trains part of the model using all data sources in a distributed manner and other parts using data from specific data sources  ...  We show, using ICU data from 58 different hospitals, that machine learning models to predict patient mortality can be trained efficiently without moving health data out of their silos using a distributed  ...  Original federated learning 0.75 0.16 Federated autonomous deep learning (FADL) 0.79 0.23  ... 
arXiv:1811.11400v2 fatcat:2a5qjxnqbza4vccc2mifz5qnla

Multi-objective Evolutionary Federated Learning [article]

Hangyu Zhu, Yaochu Jin
2019 arXiv   pre-print
Federated learning is an emerging technique used to prevent the leakage of private information.  ...  In this paper, we aim to optimize the structure of the neural network models in federated learning using a multi-objective evolutionary algorithm to simultaneously minimize the communication costs and  ...  The first experiment is conducted to compare the performance of federated learning using sparse neural network models with that using fully connected networks.  ... 
arXiv:1812.07478v2 fatcat:qham6laagre6vbyp6oxdceyzxi

Intracranial Hemorrhage Detection Using Neural Network Based Methods With Federated Learning [article]

Utkarsh Chandra Srivastava, Anshuman Singh, Dr. K. Sree Kumar
2022 arXiv   pre-print
We propose further extensions to our approach involving the deployment of federated learning.  ...  We propose a neural network approach to find and classify the condition based upon the CT scan. The model architecture implements a time distributed convolutional network.  ...  Federated Learning Federated learning, introduced by Google in 2017, is a distributed machine learning approach that enables multiinstitutional collaboration on deep learning projects without sharing patient  ... 
arXiv:2005.08644v3 fatcat:jdxb2wmfbrcg3m3hejvco65xo4

Federated Deep Learning for Cyber Security in the Internet of Things: Concepts, Applications, and Experimental Analysis

Mohamed Amine Ferrag, Othmane Friha, Leandros Maglaras, Helge Janicke, Lei Shu
2021 IEEE Access  
[121] 2020 The use of deep neural networks Qiu et al.  ...  Section V Federated Deep Learning for Cyber Security in the Internet of Things Research Questions Q1. What are the applications of federated deep learning in IoT networks?  ...  His research interests include wireless network security, network coding security, and applied cryptography.  ... 
doi:10.1109/access.2021.3118642 fatcat:222fgsvt3nh6zcgm5qt4kxe7c4
« Previous Showing results 1 — 15 out of 64,135 results