Search Results for author:
Found 3 papers, 1 papers with code
ClearMark: Intuitive and Robust Model Watermarking via Transposed Model Training
ClearMark defines a transposed model architecture allowing to use of the model in a backward fashion to interwove the watermark with the main task within all model parameters.
Avoid Adversarial Adaption in Federated Learning by Multi-Metric Investigations
We introduce Metric-Cascades (MESAS), a novel defense method for more realistic scenarios and adversary models.
CrowdGuard: Federated Backdoor Detection in Federated Learning
However, FL is susceptible to backdoor (or targeted poisoning) attacks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
