Secure Aggregation
Secure Aggregation is a cryptographic protocol in secure multi-party computation that enables a federated learning server to compute the aggregated model updates from multiple participants without revealing individual contributions, thereby preserving data privacy during collaborative model training.
487
Publications
31.8K
Citations
1.4K
Authors
569
Institutions
Publications per year
2017–2026
298
487
Practical Secure Aggregation for Privacy-Preserving Machine Learning
Keith Bonawitz, Vladimir Ivanov, Ben Kreuter et al. · 2017 · 3.4K citations
Bartosz Przydatek, Dawn Song, Adrian Perrig · 2003 · 790 citations
Privacy-Preserving Traffic Flow Prediction: A Federated Learning Approach
Yi Liu, James J. Q. Yu, Jiawen Kang et al. · IEEE Internet of Things Journal · 2020 · 678 citations · Full text
1–5 of 487
1.4K
9
h-index
9
h-index
7
h-index
7
h-index
King Abdulaziz City for Science and Technology, Saudi Arabia
6 publications · 188 citations
6
h-index
1–5 of 1.4K
569

Xidian University
Xi'an, China
13 h-index
39 publications
2.8K citations
Guangzhou University
Guangzhou, China
10 h-index
15 publications
1.4K citations

Hong Kong University of Science and Technology
Hong Kong, Hong Kong
10 h-index
14 publications
520 citations

Shanghai Jiao Tong University
Shanghai, China
10 h-index
20 publications
957 citations

Guilin University of Electronic Technology
Guilin, China
10 h-index
21 publications
1.1K citations
University of Southern California
Los Angeles, United States
9 h-index
24 publications
1.9K citations

University of Sousse
Sousse, Tunisia
9 h-index
23 publications
659 citations

University of Electronic Science and Technology of China
Chengdu, China
9 h-index
17 publications
1.8K citations
1–8 of 569
Repository · 42 publications · 1.7K citations
24
h-index
22 publications · 2K citations
20
h-index
TDSC · 12 publications · 979 citations
12
h-index
12 publications · 534 citations
11
h-index
10 publications · 1.3K citations
10
h-index
1–5