Abstract | ||
---|---|---|
Deep learning is data-hungry, and generally its performance highly depends on the amount of training data. Multiple parties can obtain better models by sharing their data and train models collaboratively. To privacy concerns, sensitive raw data of each entity can not be shared directly. In this paper, we propose a data sharing mechanism called ALRS (for Adversarial Latent Representation Sharing) that shares data representations rather than raw data, and applies adversarial example noise to protect shared representations against model inversion attacks, and achieve a balance between privacy and utility. Compared with prior collaborative learning works, ALRS requires no centralized control. We evaluate ALRS in different contexts, and the results demonstrate that our mechanism is effective against reconstruction and feature extraction attacks, while maintaining the utility of models at the same time. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1007/978-3-030-90567-5_25 | INFORMATION SECURITY AND PRIVACY, ACISP 2021 |
Keywords | DocType | Volume |
Privacy, Collaborative learning, Adversarial examples | Conference | 13083 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jikun Chen | 1 | 0 | 0.34 |
Ruoyu Deng | 2 | 0 | 0.34 |
Hongbin Chen | 3 | 0 | 0.34 |
Ruan Na | 4 | 48 | 5.63 |
Yao Liu | 5 | 1009 | 80.41 |
Chao Liu | 6 | 0 | 0.34 |
Chunhua Su | 7 | 174 | 41.11 |