Search Results for author:
Found 2 papers, 0 papers with code
Separation of Powers in Federated Learning
In this paper, we introduce TRUDA, a new cross-silo FL system, employing a trustworthy and decentralized aggregation architecture to break down information concentration with regard to a single aggregator.
Reaching Data Confidentiality and Model Accountability on the CalTrain
We also demonstrate that when malicious training participants tend to implant backdoors during model training, CALTRAIN can accurately and precisely discover the poisoned and mislabeled training data that lead to the runtime mispredictions.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
