arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.08149cs.LGstat.ML
收藏

GNNGuard:防御图神经网络对抗对抗攻击

GNNGuard: Defending Graph Neural Networks against Adversarial Attacks

Harvard University(哈佛大学)

Xiang Zhang, Marinka Zitnik

摘要:

图的深度学习方法在各种领域都取得了卓越的性能。然而,最近的研究结果表明,即使是最强大和最流行的图神经网络(GNN),图结构的小而不明显的扰动也会灾难性地降低其性能。在这里,我们开发了GNNGuard,这是一种通用算法,可以抵御各种干扰离散图结构的训练时间攻击。GNNGuard可以直接并入任何GNN。它的核心原理是检测和量化图结构和节点特征之间的关系(如果存在),然后利用这种关系来减轻攻击的负面影响。GNNGuard学习如何最好地为连接相似节点的边分配更高的权重,同时修剪不相关节点之间的边。修改后的边缘允许在底层GNN中鲁棒地传播神经消息。GNNGuard引入了两个新的组件,邻居重要性估计和逐层图存储器,我们的经验表明,这两个组件是必要的一个成功的防御。在五个GNN、三种防御方法和五个数据集(包括一个具有挑战性的人类疾病图)上,实验表明GNNGuard的平均性能比现有的防御方法高出15.3%。值得注意的是,GNNGuard可以在面对各种对抗攻击(包括针对性和非针对性攻击)时,有效地恢复GNN的最先进性能,并可以防御对异质图的攻击。

英文摘要:

Deep learning methods for graphs achieve remarkable performance across a variety of domains. However, recent findings indicate that small, unnoticeable perturbations of graph structure can catastrophically reduce performance of even the strongest and most popular Graph Neural Networks (GNNs). Here, we develop GNNGuard, a general algorithm to defend against a variety of training-time attacks that perturb the discrete graph structure. GNNGuard can be straight-forwardly incorporated into any GNN. Its core principle is to detect and quantify the relationship between the graph structure and node features, if one exists, and then exploit that relationship to mitigate negative effects of the attack.GNNGuard learns how to best assign higher weights to edges connecting similar nodes while pruning edges between unrelated nodes. The revised edges allow for robust propagation of neural messages in the underlying GNN. GNNGuard introduces two novel components, the neighbor importance estimation, and the layer-wise graph memory, and we show empirically that both components are necessary for a successful defense. Across five GNNs, three defense methods, and five datasets,including a challenging human disease graph, experiments show that GNNGuard outperforms existing defense approaches by 15.3% on average. Remarkably, GNNGuard can effectively restore state-of-the-art performance of GNNs in the face of various adversarial attacks, including targeted and non-targeted attacks, and can defend against attacks on heterophily graphs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑