R Doku, DB Rawat - 2021 IEEE 18th Annual Consumer …, 2021 - ieeexplore.ieee.org
Edge Computing (EC) has seen a continuous rise in its popularity as it provides a solution to the latency and communication issues associated with edge devices transferring data to …
J Zhang, B Chen, X Cheng, HTT Binh… - IEEE Internet of Things …, 2020 - ieeexplore.ieee.org
Edge computing is a key-enabling technology that meets continuously increasing requirements for the intelligent Internet-of-Things (IoT) applications. To cope with the …
H Li, X Sun, Z Zheng - Advances in Neural Information …, 2022 - proceedings.neurips.cc
We propose a model-based reinforcement learning framework to derive untargeted poisoning attacks against federated learning (FL) systems. Our framework first approximates …
With the massive amounts of data generated by industrial Internet of Things (IIoT) devices at all moments, federated learning (FL) enables these distributed distrusted devices to …
P Gupta, K Yadav, BB Gupta, M Alazab… - Computers & …, 2023 - Elsevier
Data poisoning attack is one of the common attacks that decreases the performance of a model in edge machine learning. The mechanism used in most of the existing data …
X Zhou, M Xu, Y Wu, N Zheng - Future Internet, 2021 - mdpi.com
Federated learning is a novel distributed learning framework, which enables thousands of participants to collaboratively construct a deep learning model. In order to protect …
While recent works have indicated that federated learning (FL) may be vulnerable to poisoning attacks by compromised clients, their real impact on production FL systems is not …
Y Mao, X Yuan, X Zhao, S Zhong - … , October 4–8, 2021, Proceedings, Part …, 2021 - Springer
Training a deep neural network requires substantial data and intensive computing resources. Unaffordable price holds back many potential applications of deep learning …
Federated learning (FL) is an emerging paradigm for distributed training of large-scale deep neural networks in which participants' data remains on their own devices with only model …