Feature-Based Graph Backdoor Attack in the Node Classification Task

Abstract

Graph neural networks (GNNs) have shown significant performance in various practical applications due to their strong learning capabilities. Backdoor attacks are a type of attack that can produce hidden attacks on machine learning models. GNNs take backdoor datasets as input to produce an adversary-specified output on poisoned data but perform normally on clean data, which can have grave implications for applications. Backdoor attacks are under-researched in the graph domain, and almost existing graph backdoor attacks focus on the graph-level classification task. To close this gap, we propose a novel graph backdoor attack that uses node features as triggers and does not need knowledge of the GNNs parameters. In the experiments, we find that feature triggers can destroy the feature spaces of the original datasets, resulting in GNNs inability to identify poisoned data and clean data well. An adaptive method is proposed to improve the performance of the backdoor model by adjusting the graph structure. We conducted extensive experiments to validate the effectiveness of our model on three benchmark datasets.

Defense Strategies Toward Model Poisoning Attacks in Federated Learning: A Survey

“…The defense methods at this stage primarily focus on data poisoning backdoor attacks. The existing works show reasonable defense performance on label-flipping backdoor attack [186], [187] and trigger-based backdoor attack [188], [189]. In the rest of this section, two typical defense methods implemented during the local training phase are analyzed, and their limitations are discussed accordingly.…”