Search Results for author:
Found 5 papers, 1 papers with code
FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learning
Existing defenses against poisoning attacks in FL have several limitations, such as relying on specific assumptions about attack types and strategies or data distributions or not sufficiently robust against advanced injection techniques and strategies and simultaneously maintaining the utility of the aggregated model.
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.
ESCORT: Ethereum Smart COntRacTs Vulnerability Detection using Deep Neural Network and Transfer Learning
When extended to new vulnerability types, ESCORT yields an average F1-score of 93%.
