Search Results for author:
Found 3 papers, 2 papers with code
Defending Against Backdoor Attacks by Layer-wise Feature Analysis
We find out that the feature difference between benign and poisoned samples tends to be maximum at a critical layer, which is not always the one typically used in existing defenses, namely the layer before fully-connected layers.
Enhanced Security and Privacy via Fragmented Federated Learning
To tackle the accuracy-privacy-security conflict, we propose {\em fragmented federated learning} (FFL), in which participants randomly exchange and mix fragments of their updates before sending them to the server.
Defending against the Label-flipping Attack in Federated Learning
The label-flipping (LF) attack is a targeted poisoning attack where the attackers poison their training data by flipping the labels of some examples from one class (i. e., the source class) to another (i. e., the target class).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
