230 Hits in 5.9 sec

Byzantine-robust Federated Learning through Spatial-temporal Analysis of Local Model Updates [article]

Zhuohang Li, Luyang Liu, Jiaxin Zhang, Jian Liu
2021 arXiv   pre-print
Federated Learning (FL) enables multiple distributed clients (e.g., mobile devices) to collaboratively train a centralized model while keeping the training data locally on the client.  ...  However, Byzantine clients that send incorrect or disruptive updates due to system failures or adversarial attacks may disturb the joint learning process, consequently degrading the performance of the  ...  CONCLUSION In this work, we propose a new method to achieve Byzantine-resilient FL through analyzing the spatial-temporal patterns of the clients' updates.  ... 
arXiv:2107.01477v2 fatcat:e4zvglywcfbmbmi2kkyeohlwna

Federated Learning: A Signal Processing Perspective [article]

Tomer Gafni, Nir Shlezinger, Kobi Cohen, Yonina C. Eldar, H. Vincent Poor
2021 arXiv   pre-print
Federated learning is an emerging machine learning paradigm for training models across multiple edge devices holding local datasets, without explicitly exchanging the data.  ...  Consequently, dedicated schemes derived from these areas are expected to play an important role in the success of federated learning and the transition of deep learning from the domain of centralized servers  ...  Byzantine-Robust Federated Learning Consider a federated learning system with N users possessing datasets of identical sizes, i.e., |D i | ≡ n.  ... 
arXiv:2103.17150v2 fatcat:pktgiqowsjbklfnj753ehdbnhu

ARTICONF: Towards a Smart Social Media Ecosystem in a Blockchain Federated Environment

Radu Prodan, Nishant Saurabh, Zhiming Zhao, Kate Orton-Johnson, Antorweep Chakravorty, Aleksandar Karadimce, Alexandre Ulisses
2019 Zenodo  
The ARTICONF project funded by the European Horizon 2020 program addresses issues of trust, time-criticality and democratisation for a new generation of federated infrastructure, to fulfil the privacy,  ...  edge-based infrastructure meeting application runtime requirements; and (4) enhance monetary inclusion in collaborative models through cognition and knowledge supply chains.  ...  This is seamlessly coupled with distributed blockchain-based services for early alert, real-time tracking and updated data triggers for reach and engagement analysis of events.  ... 
doi:10.5281/zenodo.3580716 fatcat:rep63fbjdjaclchcbqcydocm6e

OCTOPUS: Overcoming Performance andPrivatization Bottlenecks in Distributed Learning [article]

Shuo Wang, Surya Nepal, Kristen Moore, Marthie Grobler, Carsten Rudolph, Alsharif Abuadbba
2022 arXiv   pre-print
Federated learning enables distributed participants to collaboratively learn a commonly-shared model while holding data locally.  ...  The diversity and quantity of data warehouses, gathering data from distributed devices such as mobile devices, can enhance the success and robustness of machine learning algorithms.  ...  Furthermore, the dynamic dictionary update could consider the spatial and temporal bias associated with local data.  ... 
arXiv:2105.00602v2 fatcat:2avblpysobdl3hmgriss7umypq

Table of Contents [EDICS]

2020 IEEE Transactions on Signal Processing  
Luo 3644 Federated Variance-Reduced Stochastic Gradient Descent With Robustness to Byzantine Attacks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Rajawat 2287 Modeling of Spatio-Temporal Hawkes Processes With Randomized Kernels . . . . . . . . . . . . . . . . . . F. Ilhan and S. S.  ...  Wang 4293 Localization of a Moving Source by Frequency Measurements . . . . . . . . . . . . . . . . . M. M. Ahmed, K. C. Ho, and G.  ... 
doi:10.1109/tsp.2020.3045363 fatcat:wcnvdcy3rvhblh7rtxfe6gz4re

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
Edge intelligence refers to a set of connected systems and devices for data collection, caching, processing, and analysis in locations close to where data is captured based on artificial intelligence.  ...  The aim of edge intelligence is to enhance the quality and speed of data processing and protect the privacy and security of the data.  ...  Blanchard et al. evaluate the Byzantine resilience of SGD in federated learning [163] . Byzantine refers to arbitrary failures in federated learning, such as erroneous data and software bugs.  ... 
arXiv:2003.12172v2 fatcat:xbrylsvb7bey5idirunacux6pe

2020 Index IEEE Transactions on Signal Processing Vol. 68

2020 IEEE Transactions on Signal Processing  
Ibrahim, M.S., +, TSP 2020 1897-1909 Federated Variance-Reduced Stochastic Gradient Descent With Robustness to Byzantine Attacks. Wu, Z., +, TSP 2020 4583-4596 Functional Nonlinear Sparse Models.  ...  Markovsky, I., +, TSP 2020 3064-3073 Dictionary Learning With BLOTLESS Update. Yu, Q., +, TSP 2020 1635-1645 Distributed Approximate Newton's Method Robust to Byzantine Attackers.  ...  Topological Sweep for Multi-Target Detection of Geostationary Space Objects. Liu, D., +, TSP 2020  ... 
doi:10.1109/tsp.2021.3055469 fatcat:6uswtuxm5ba6zahdwh5atxhcsy

Asynchronous Federated Learning on Heterogeneous Devices: A Survey [article]

Chenhao Xu, Youyang Qu, Yong Xiang, Longxiang Gao
2022 arXiv   pre-print
Federated learning (FL) is experiencing a fast booming with the wave of distributed machine learning.  ...  In the FL paradigm, the global model is aggregated on the centralized aggregation server according to the parameters of local models instead of local training data, mitigating privacy leakage caused by  ...  Federated Learning The concept of FL is first introduced in [22] .  ... 
arXiv:2109.04269v3 fatcat:bcix56mg7zev7hzav4rahkycai

Table of Contents

2020 IEEE Transactions on Signal Processing  
Khalid 4568 Federated Variance-Reduced Stochastic Gradient Descent With Robustness to Byzantine Attacks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Granström 4933 Modeling of Spatio-Temporal Hawkes Processes With Randomized Kernels . . . . . . . . . . . . . . . . . . F. Ilhan and S. S.  ... 
doi:10.1109/tsp.2020.3042287 fatcat:nh7viihaozhd7li3txtadnx5ui

A Comprehensive Review on Blockchains for Internet of Vehicles: Challenges and Directions [article]

Brian Hildebrand, Mohamed Baza, Tara Salman, Fathi Amsaad, Abdul Razaqu, Abdullah Alourani
2022 arXiv   pre-print
We also present in-depth applications federated learning (FL) applications for BIoVs.  ...  Blockchain offers the benefits of trustworthiness, immutability, and mitigates the problem of single point of failure and other attacks.  ...  In FL, however, the size of the datasets for Central Aggregator Local Model Local Dataset Local Model Local Dataset Local Model Update Local Model Update Global Model Global Model Fig. 8 .  ... 
arXiv:2203.10708v1 fatcat:sozptzz5l5a27oh5rukujcg32a

Genetic CFL: Hyperparameter Optimization in Clustered Federated Learning

Shaashwat Agrawal, Sagnik Sarkar, Mamoun Alazab, Praveen Kumar Reddy Maddikunta, Thippa Reddy Gadekallu, Quoc-Viet Pham, Rodolfo E. Haber
2021 Computational Intelligence and Neuroscience  
Federated learning (FL) is a distributed model for deep learning that integrates client-server architecture, edge computing, and real-time intelligence.  ...  FL has the capability of revolutionizing machine learning (ML) but lacks in the practicality of implementation due to technological limitations, communication overhead, non-IID (independent and identically  ...  “On the byzantine robustness of clustered federated learning,” org/abs/1806.00582.  ... 
doi:10.1155/2021/7156420 pmid:34840562 pmcid:PMC8616689 fatcat:256gkfkbxnb3liol7pto6b6c4a

When Attackers Meet AI: Learning-empowered Attacks in Cooperative Spectrum Sensing [article]

Zhengping Luo, Shangqing Zhao, Zhuo Lu, Jie Xu, Yalin E. Sagduyu
2020 arXiv   pre-print
Based on the black-box nature of the fusion center in cooperative spectrum sensing, our new perspective is to make the adversarial use of machine learning to construct a surrogate model of the fusion center's  ...  decision model.  ...  spatially and temporally varying nature of the wireless environment.  ... 
arXiv:1905.01430v2 fatcat:kau4vpl7d5gtpgstd75xv7glk4

Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications [article]

Khaled B. Letaief, Yuanming Shi, Jianmin Lu, Jianhua Lu
2021 arXiv   pre-print
In this paper, we shall provide our vision for scalable and trustworthy edge AI systems with integrated design of wireless communication strategies and decentralized machine learning models.  ...  However, state-of-the-art deep learning and big data analytics based AI systems require tremendous computation and communication resources, causing significant latency, energy consumption, network congestion  ...  To address Byzantine attacks (i.e., the faulty edge device can behave arbitrarily badly by modifying its local updates) in FL with a server-client architecture, various robust and secure model aggregation  ... 
arXiv:2111.12444v1 fatcat:crrbtfylvjeihogumggdnxcbpq

Federated Learning for Big Data: A Survey on Opportunities, Applications, and Future Directions [article]

Thippa Reddy Gadekallu, Quoc-Viet Pham, Thien Huynh-The, Sweta Bhattacharya, Praveen Kumar Reddy Maddikunta, Madhusanka Liyanage
2021 arXiv   pre-print
To overcome this challenge, federated learning (FL) appeared to be a promising learning technique.  ...  The potential of big data can be realized via analytic and learning techniques, in which the data from various sources is transferred to a central cloud for central storage, processing, and training.  ...  Acknowledgement We acknowledge the authors (Dinh, Fang, Pubudu) for the contribution of our (blockchain -big data) development.  ... 
arXiv:2110.04160v2 fatcat:3y2kmamdbrfmrjdxv3zh47yphu

A Deep Learning Perspective on Connected Automated Vehicle (CAV) Cybersecurity and Threat Intelligence [article]

Manoj Basnet, Mohd. Hasan Ali
2021 arXiv   pre-print
The frontiers in deep learning, namely Meta-Learning and Federated Learning, along with their challenges have been included in the chapter.  ...  training, adversarial threats to the model, and poor generalizability of the model under out of data distributions.  ...  algorithm derived from meta-learning to learn a new task FEDERATED LEARNING Federated learning (FL) is a machine learning framework where multiple nodes collaboratively train a model with local data  ... 
arXiv:2109.10763v1 fatcat:tigj5x6pnrbmrbf3my46ynr4we
« Previous Showing results 1 — 15 out of 230 results