论文标题
后门攻击图形神经网络
Backdoor Attacks to Graph Neural Networks
论文作者
论文摘要
在这项工作中，我们向图形神经网络（GNN）提出了第一次后门攻击。具体来说，我们向GNN提出了\ emph {基于子图的后门攻击}以进行图形分类。在我们的后门攻击中，一旦将预定义的子图注入了测试图，GNN分类器将预测测试图的攻击者选择的目标标签。我们在三个现实世界图数据集上的经验结果表明，我们的后门攻击是有效的，对GNN的预测准确性的影响很小。此外，我们将基于随机的平滑认证辩护概括为防御我们的后门攻击。我们的经验结果表明，在某些情况下，防御有效，但在其他情况下无效，强调了我们的后门攻击的新防御需求。
In this work, we propose the first backdoor attack to graph neural networks (GNN). Specifically, we propose a \emph{subgraph based backdoor attack} to GNN for graph classification. In our backdoor attack, a GNN classifier predicts an attacker-chosen target label for a testing graph once a predefined subgraph is injected to the testing graph. Our empirical results on three real-world graph datasets show that our backdoor attacks are effective with a small impact on a GNN's prediction accuracy for clean testing graphs. Moreover, we generalize a randomized smoothing based certified defense to defend against our backdoor attacks. Our empirical results show that the defense is effective in some cases but ineffective in other cases, highlighting the needs of new defenses for our backdoor attacks.
