2 papers
cs.CR2025
Local Differential Privacy is Not Enough: A Sample Reconstruction Attack against Federated Learning with Local Differential Privacy
Zhichao You, Xuewen Dong, Shujun Li +3
Reconstruction attacks against federated learning (FL) aim to reconstruct users' samples through users' uploaded gradients. Local differential privacy (LDP) is regarded as an effec…
cs.CR2024
MORSE: An Efficient Homomorphic Secret Sharing Scheme Enabling Non-Linear Operation
Weiquan Deng, Bowen Zhao, Yang Xiao +3
Homomorphic secret sharing (HSS) enables two servers to locally perform functions on encrypted data directly and obtain the results in the form of shares. A Paillier-based HSS solu…