Open access
2026
SURGE: Sparse Updates With Randomized Guarding and Selective Encryption for Secure Federated Learning
SURGE targets empirical attack resistance under the honest-but-curious server model, rather than a formal privacy guarantee, and drives membership inference performance close to random guessing and substantially degrades the quality of gradient inversion reconstructions.
Xuanchi Li, Yiting Tan, Jing Wen et al.
· IEEE Access · 0 citations