Copyright protection framework for federated learning models against collusion attacks
Y Luo, Y Li, S Qin, Q Fu, J Liu - Information Sciences, 2024 - Elsevier
Federated learning (FL) models are constructed by multiple participants who provide their
training datasets and collaborate in joint training. However, training and deployment …
training datasets and collaborate in joint training. However, training and deployment …
Privacy-preserving federated learning compatible with robust aggregators
Federated learning has emerged as a promising paradigm for collaborative machine
learning across decentralized devices, offering the benefit of model training without …
learning across decentralized devices, offering the benefit of model training without …
Self-adaptive asynchronous federated optimizer with adversarial sharpness-aware minimization
The past years have witnessed the success of a distributed learning system called
Federated Learning (FL). Recently, asynchronous FL (AFL) has demonstrated its potential in …
Federated Learning (FL). Recently, asynchronous FL (AFL) has demonstrated its potential in …
[HTML][HTML] PRoT-FL: A privacy-preserving and robust Training Manager for Federated Learning
Federated Learning emerged as a promising solution to enable collaborative training
between organizations while avoiding centralization. However, it remains vulnerable to …
between organizations while avoiding centralization. However, it remains vulnerable to …
Decentralized and robust privacy-preserving model using blockchain-enabled Federated Deep Learning in intelligent enterprises
Abstract In Federated Deep Learning (FDL), multiple local enterprises are allowed to train a
model jointly. Then, they submit their local updates to the central server, and the server …
model jointly. Then, they submit their local updates to the central server, and the server …
Enhancing Federated Learning Robustness using Locally Benignity-Assessable Bayesian Dropout
J Xue, S Sun, M Liu, Q Li, K Xu - IEEE Transactions on …, 2025 - ieeexplore.ieee.org
Federated Learning (FL) has emerged as a privacy-preserving training paradigm, which
enables distributed devices to jointly learn a shared model without raw data sharing …
enables distributed devices to jointly learn a shared model without raw data sharing …