Byzantine-robust decentralized federated learning

M Fang, Z Zhang, Hairi, P Khanduri, J Liu, S Lu… - Proceedings of the …, 2024 - dl.acm.org
Federated learning (FL) enables multiple clients to collaboratively train machine learning
models without revealing their private training data. In conventional FL, the system follows …

Fltracer: Accurate poisoning attack provenance in federated learning

X Zhang, Q Liu, Z Ba, Y Hong, T Zheng… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Federated Learning (FL) is a promising distributed learning approach that enables multiple
clients to collaboratively train a shared global model. However, recent studies show that FL …

Depriving the Survival Space of Adversaries Against Poisoned Gradients in Federated Learning

J Lu, S Hu, W Wan, M Li, LY Zhang… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Federated learning (FL) allows clients at the edge to learn a shared global model without
disclosing their private data. However, FL is susceptible to poisoning attacks, wherein an …

FedQV: Leveraging Quadratic Voting in Federated Learning

T Chu, N Laoutaris - Proceedings of the ACM on Measurement and …, 2024 - dl.acm.org
Federated Learning (FL) permits different parties to collaboratively train a global model
without disclosing their respective local labels. A crucial step of FL, that of aggregating local …

Privacy-Preserving Federated Learning With Improved Personalization and Poison Rectification of Client Models

Y Cao, J Zhang, Y Zhao, H Shen… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Federated Learning (FL), a secure and emerging distributed learning paradigm, has
garnered significant interest in the Internet of Things (IoT) domain. However, it remains …

Evaluating Security and Robustness for Split Federated Learning against Poisoning Attacks

X Wu, H Yuan, X Li, J Ni, R Lu - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Split federated learning (SFL) is a recently proposed distributed collaborative learning
architecture that integrates federated learning (FL) with split learning (SL), offering an …

Location leakage in federated signal maps

E Bakopoulou, M Yang, J Zhang… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
We consider the problem of predicting cellular network performance (signal maps) from
measurements collected by several mobile devices. We formulate the problem within the …

Strengthening Privacy in Robust Federated Learning through Secure Aggregation

T Chu, D İşler, N Laoutaris - Workshop on Artificial …, 2024 - dspace.networks.imdea.org
Federated Learning (FL) has evolved into a pivotal paradigm for collaborative machine
learning, enabling a centralised server to compute a global model by aggregating the local …

FL-Torrent: decentralised AI for the masses

Á García-Recuero, N Laoutaris - 12th IMDEA Networks …, 2022 - dspace.networks.imdea.org
Google has made Federated Learning (FL) readily available to the public with their software
and APIs as TensorFlow, but vendor lock-in is still a problem for experimental deployments …