CRAIApr 23, 2024

Leverage Variational Graph Representation For Model Poisoning on Federated Learning

arXiv:2404.15042v220 citationsh-index: 18IEEE Trans Neural Netw Learn Syst
Originality Highly original
AI Analysis

This poses a severe threat to federated learning systems by enabling stealthy attacks that compromise model integrity without data access.

The paper introduces a model poisoning attack on federated learning that uses a variational graph autoencoder to generate malicious models without accessing training data, causing a gradual drop in accuracy and evading detection by existing defenses.

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 the benign local models and the training data features, adversarially regenerates the graph structure, and generates malicious local models using the adversarial graph structure and benign models' features. Moreover, a new attacking algorithm is presented to train the malicious local models using VGAE and sub-gradient descent, while enabling an optimal selection of the benign local models for training the VGAE. Experiments demonstrate a gradual drop in FL accuracy under the proposed VGAE-MP attack and the ineffectiveness of existing defense mechanisms in detecting the attack, posing a severe threat to FL.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes