论文标题
具有乘数交替方向方法对图神经网络上的可扩展对抗性攻击
Scalable Adversarial Attack on Graph Neural Networks with Alternating Direction Method of Multipliers
论文作者
论文摘要
图形神经网络（GNN）在分析图形结构数据方面已经达到了高性能，并已广泛部署在安全至关重要的地区，例如财务和自动驾驶。但是，只有少数作品探索了GNN对对抗攻击的鲁棒性，并且它们的设计通常受到输入数据集的规模限制（即，专注于只有数千个节点的小图）。在这项工作中，我们提出，下垂，是第一个具有交替方向乘数方法（ADMM）的可扩展对抗攻击方法。我们首先将大尺度图解散到几个较小的图形分区中，并将原始问题投入到几个子问题中。然后，我们建议在图形拓扑和节点特征上使用投影梯度下降来解决这些子问题，与传统攻击方法相比，它们导致存储器消耗率要低得多。严格的实验进一步表明，与最先进的方法相比，SAG可以显着减少计算和内存开销，从而使SAG适用于具有较大节点和边缘的图形。
Graph neural networks (GNNs) have achieved high performance in analyzing graph-structured data and have been widely deployed in safety-critical areas, such as finance and autonomous driving. However, only a few works have explored GNNs' robustness to adversarial attacks, and their designs are usually limited by the scale of input datasets (i.e., focusing on small graphs with only thousands of nodes). In this work, we propose, SAG, the first scalable adversarial attack method with Alternating Direction Method of Multipliers (ADMM). We first decouple the large-scale graph into several smaller graph partitions and cast the original problem into several subproblems. Then, we propose to solve these subproblems using projected gradient descent on both the graph topology and the node features that lead to considerably lower memory consumption compared to the conventional attack methods. Rigorous experiments further demonstrate that SAG can significantly reduce the computation and memory overhead compared with the state-of-the-art approach, making SAG applicable towards graphs with large size of nodes and edges.
