R Hu, Y Guo, Y Gong - IEEE Transactions on Mobile Computing, 2023 - ieeexplore.ieee.org
Federated learning (FL) that enables edge devices to collaboratively learn a shared model while keeping their training data locally has received great attention recently and can protect …
X Yin, Y Zhu, J Hu - ACM Computing Surveys (CSUR), 2021 - dl.acm.org
The past four years have witnessed the rapid development of federated learning (FL). However, new privacy concerns have also emerged during the aggregation of the …
B Wang, Y Chen, H Jiang, Z Zhao - IEEE Internet of Things …, 2023 - ieeexplore.ieee.org
Since traditional federated learning (FL) algorithms cannot provide sufficient privacy guarantees, an increasing number of approaches apply local differential privacy (LDP) …
Z Chuanxin, S Yi, W Degang - Proceedings of the 2020 2nd international …, 2020 - dl.acm.org
In recent years, federated learning has rapidly become a new research hotspot in the field of secure machine learning. However, unprotected traditional federated learning can easily …
L Sun, J Qian, X Chen - arXiv preprint arXiv:2007.15789, 2020 - arxiv.org
Train machine learning models on sensitive user data has raised increasing privacy concerns in many areas. Federated learning is a popular approach for privacy protection …
X Shen, H Jiang, Y Chen, B Wang, L Gao - Entropy, 2023 - mdpi.com
As a popular machine learning method, federated learning (FL) can effectively solve the issues of data silos and data privacy. However, traditional federated learning schemes …
Advanced adversarial attacks such as membership inference and model memorization can make federated learning (FL) vulnerable and potentially leak sensitive private data. Local …
J Hu, Z Wang, Y Shen, B Lin, P Sun… - IEEE/ACM …, 2023 - ieeexplore.ieee.org
Federated learning (FL) requires frequent uploading and updating of model parameters, which is naturally vulnerable to gradient leakage attacks (GLAs) that reconstruct private …
Federated learning (FL), as a type of distributed machine learning, is capable of significantly preserving clients' private data from being exposed to adversaries. Nevertheless, private …