About
Contact & Profiles
A5101565020
Research Areas
- Stochastic Gradient Optimization Techniques
- Privacy-Preserving Technologies in Data
- Cryptography and Data Security
Fuzhou University
2023
Federated learning (FL) is a novel machine framework in which models are built jointly by multiple parties. We investigate the privacy preservation of XGBoost, gradient boosting decision tree (GBDT) model, context FL. While recent work relies on cryptographic schemes to preserve model gradients, these methods computationally expensive. In this paper, we propose an adaptive privacy-preserving algorithm based differential (DP), more efficient. Our perturbs individual data computing mean per...
10.1145/3590003.3590051
article
EN
2023-03-17
Coming Soon ...