Leverage Variational Graph Representation For Model Poisoning on Federated Learning

arXiv:2404.15042v1 Announce Type: new
Abstract: This paper puts forth a new training data-untethered model poisoning (MP) attack on federated learning (FL). The new MP attack extends an adversarial variational graph autoencoder (VGAE) to create malicious local models based solely on the benign local models overheard without any access to the training data of FL. Such an advancement leads to the VGAE-MP attack that is not only efficacious but also remains elusive to detection. VGAE-MP attack extracts graph structural correlations among …

access adversarial arxiv attack cs.ai cs.cr data federated federated learning graph local malicious poisoning representation training training data untethered