<ul><li>This paper presents an empirical analysis of federated learning models subjected to label-flipping adversarial attacks.</li><li>Various models such as MLR, SVC, MLP, CNN, RNN, Random Forest, XGBoost, and LSTM are considered.</li><li>Experiments are conducted with different percentages of adversarial clients and flipped labels.</li><li>The study reveals variations in the robustness of models to these attack vectors.</li></ul>

An Empirical Analysis of Federated Learning Models Subject to Label-Flipping Adversarial Attack

Discover more