Results 51 to 60 of about 17,879 (167)

Meta-federated learning

Due to its distributed methodology alongside its privacy-preserving features, Federated Learning (FL) is vulnerable to training time adversarial attacks. In this study, our focus is on backdoor attacks in which the adversary's goal is to cause targeted misclassifications for inputs embedded with an adversarial trigger while maintaining an acceptable ...
Omid Aramoon, Pin-Yu Chen, Gang Qu 0001, Yuan Tian 0001   +3 more
openaire   +2 more sources

Distributed consensus problem with caching on federated learning framework

International Journal of Distributed Sensor Networks, 2022
Federated learning framework facilitates more applications of deep learning algorithms on the existing network architectures, where the model parameters are aggregated in a centralized manner.
Xin Yan, Yiming Qin, Xiaodong Hu, Xiaoling Xiao   +3 more
doaj   +1 more source

A survey of security threats in federated learning

Complex & Intelligent Systems
Federated learning is a distributed machine learning paradigm that emerged as a solution to the need for privacy protection in artificial intelligence.
Yunhao Feng, Yanming Guo, Yinjian Hou, Yulun Wu, Mingrui Lao, Tianyuan Yu, Gang Liu   +6 more
doaj   +1 more source

A Survey of Differential Privacy Techniques for Federated Learning

IEEE Access
The problem of data privacy protection in the information age deserves people’s attention. As a distributed machine learning technology, federated learning can effectively solve the problem of privacy security and data silos.
Wang Xin, Li Jiaqian, Ding Xueshuang, Zhang Haoji, Sun Lianshan   +4 more
doaj   +1 more source

Research advances on privacy protection of federated learning

大数据, 2021
To this end, many laws and regulations on privacy protection have been introduced, and the phenomenon of data-island has become a major bottleneck hindering the development of big data and artificial intelligence technology.Federated learning has ...
Jianzong WANG, Lingwei KONG, Zhangcheng HUANG, Linjie CHEN, Yi LIU, Chunxi LU, Jing XIAO   +6 more
doaj  

Accelerating Fair Federated Learning: Adaptive Federated Adam

IEEE Transactions on Machine Learning in Communications and Networking
Federated learning is a distributed and privacy-preserving approach to train a statistical model collaboratively from decentralized data held by different parties. However, when the datasets are not independent and identically distributed, models trained
Li Ju, Tianru Zhang, Salman Toor, Andreas Hellander   +3 more
doaj   +1 more source

An Watermarking Framework of Active Protection Model for Secure Federated Learning [PDF]

Jisuanji gongcheng
As a new paradigm in deep learning, federated learning allows multiple parties to jointly train deep learning models while ensuring that data remains on the clients' local devices.
CHEN Xianyi, DING Sizhe, WANG Kang, YAN Leiming, FU Zhangjie
doaj   +1 more source

Partial Federated Learning

CoRR
Federated Learning (FL) is a popular algorithm to train machine learning models on user data constrained to edge devices (for example, mobile phones) due to privacy concerns. Typically, FL is trained with the assumption that no part of the user data can be egressed from the edge.
Tiantian Feng, Anil Ramakrishna, Jimit Majmudar, Charith Peris, Jixuan Wang, Clement Chung, Richard S. Zemel, Morteza Ziyadi, Rahul Gupta 0001   +8 more
openaire   +2 more sources

Federated Balanced Learning

CoRR
Federated learning is a paradigm of joint learning in which clients collaborate by sharing model parameters instead of data. However, in the non-iid setting, the global model experiences client drift, which can seriously affect the final performance of the model.
Jiaze Li, Haoran Xu, Wanyi Wu, Changwei Wang 0001, Shuaiguang Li, Jianzhong Ju, Zhenbo Luo, Jian Luan 0001, Youyang Qu, Longxiang Gao, Xudong Yang, Lumin Xing   +11 more
openaire   +2 more sources

Federated Learning Playground

Proceedings of the AAAI Conference on Artificial Intelligence
We present Federated Learning Playground, an interactive browser-based platform inspired by and extends TensorFlow Playground that teaches core Federated Learning (FL) concepts. Users can experiment with heterogeneous client data distributions, model hyperparameters, and aggregation algorithms directly in the browser without coding or system setup, and
Bryan Shan Guanrong, Alysa Ziying Tan, Han Yu 0001   +2 more
openaire   +2 more sources