PAPI-Attack

code for "Poisoning-assisted property inference attack against federated learning"

environment: Python 3.7, PyTorch 1.0, scikit-learn 0.21

dataset: LFW (http://vis-www.cs.umass.edu/lfw/index.html#download)

built based on the code of "How to Backdoor Federated Learning" (https://github.com/ebagdasa/backdoor_federated_learning)