Title | ||
---|---|---|
PPCL: Privacy-preserving collaborative learning for mitigating indirect information leakage |
Abstract | ||
---|---|---|
•A novel privacy-preserving framework is proposed for collaborative learning, targeting to alleviate the indirect information leakage for dishonest clients or clients collusion situation.•Our scheme employs network pruning operations to make our solution converge fast to improve the computation efficiency.•We give the formal security analysis to show the privacy leakage is negligible in our scheme.•We conduct the experiments on MNIST dataset to validate our scheme achieves a good performance. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1016/j.ins.2020.09.064 | Information Sciences |
Keywords | DocType | Volume |
Collaborative Learning,Privacy-Preserving,Network Transformation,Network Pruning | Journal | 548 |
ISSN | Citations | PageRank |
0020-0255 | 2 | 0.37 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hongyang Yan | 1 | 32 | 7.09 |
Li Hu | 2 | 3 | 1.40 |
Xiaoyu Xiang | 3 | 2 | 0.37 |
Zheli Liu | 4 | 356 | 28.79 |
Xu Yuan | 5 | 61 | 24.92 |