Search Results for author:
Found 2 papers, 1 papers with code
Towards Efficient and Certified Recovery from Poisoning Attacks in Federated Learning
Federated learning (FL) is vulnerable to poisoning attacks, where malicious clients manipulate their updates to affect the global model.
AST: Effective Dataset Distillation through Alignment with Smooth and High-Quality Expert Trajectories
We observed that the smoothness of expert trajectories has a significant impact on subsequent student parameter alignment.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
