adversarial-5
Model Posioning
3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in model-posioning-11
Trend
Dataset
Best Model
Actions
No benchmarks available.
Libraries
iUse these libraries to find model-posioning-11 models and implementations
Datasets
No datasets available.
Subtasks
No subtasks available.
Most implemented papers
BARFED: Byzantine Attack-Resistant Federated Averaging Based on Outlier Elimination
Ece Isik-Polat, G. Polat, Altan Koçyiğit•Thu Dec 31 2020
This work proposes a defense algorithm called BARFED that does not make any assumptions about data distribution, update similarity of participants, or the ratio of the malicious participants and mainly considers the outlier status of participant updates for each layer of the model architecture based on the distance to the global model.
2