EPIDL: Towards efficient and privacy-preserving inference in deep learning.
Concurr. Comput. Pract. Exp., June, 2024
Efficient Byzantine-Robust and Provably Privacy-Preserving Federated Learning.
CoRR, 2024
A Learning-Based Attack Framework to Break SOTA Poisoning Defenses in Federated Learning.
CoRR, 2024
Breaking State-of-the-Art Poisoning Defenses to Federated Learning: An Optimization-Based Attack Framework.
Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024